{"generated_at":"2026-10-29T20:43:55.507Z","providers":[{"key":"deepinfra","name":"DeepInfra","model_count":91,"status":"ok"},{"key":"ember","name":"EmberCloud","model_count":20,"status":"ok"},{"key":"wafer","name":"Wafer","model_count":10,"status":"ok"},{"key":"synthetic","name":"Synthetic","model_count":13,"status":"ok"},{"key":"sambanova","name":"SambaNova","model_count":6,"status":"ok"},{"key":"hyper","name":"HyperCharm","model_count":23,"status":"ok"},{"key":"sference","name":"Sference","model_count":8,"status":"ok"},{"key":"neuralwatt","name":"Neuralwatt","model_count":27,"status":"ok"},{"key":"merius","name":"Tarmis","model_count":0,"status":"error: fetch failed: fetch failed"},{"key":"aster","name":"Aster Labs","model_count":5,"status":"ok"},{"key":"arilo","name":"Arilo.id","model_count":1,"status":"ok"},{"key":"avian","name":"Avian","model_count":19,"status":"ok"},{"key":"batchrate","name":"Batchrate","model_count":8,"status":"ok"},{"key":"coralbricks","name":"CoralBricks","model_count":2,"status":"ok"},{"key":"singularity","name":"SingularityAPI","model_count":21,"status":"ok"},{"key":"runinfra","name":"RunInfra","model_count":8,"status":"ok"},{"key":"llmgateway","name":"LLM Gateway (differential)","model_count":103,"status":"ok"},{"key":"runanywhere","name":"Wally Cloud (RunAnywhere)","model_count":9,"status":"ok"},{"key":"engy","name":"engy","model_count":9,"status":"ok"},{"key":"openscale","name":"OpenScale","model_count":9,"status":"ok"},{"key":"zro","name":"Zro","model_count":5,"status":"ok (snapshot)"},{"key":"openrouter","name":"OpenRouter (de-aggregated)","model_count":1217,"status":"ok"},{"key":"xiaomimimo","name":"Xiaomimimo","model_count":3,"status":"ok"},{"key":"makora","name":"Makora","model_count":6,"status":"ok"},{"key":"opencode","name":"OpenCode Go","model_count":36,"status":"ok"},{"key":"umans","name":"Umans AI","model_count":3,"status":"ok"},{"key":"refuseless","name":"Refuseless","model_count":5,"status":"ok"}],"models":[{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"deepseek-ai/DeepSeek-V4-Pro-0813","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1.2999999999999998,"output":2.5999999999999996,"cache_read":0.10000000399999999,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":384000,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"openai/gpt-oss-120b","name":"openai/gpt-oss-120b","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.037,"output":0.16999999999999998,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-120b","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"inclusionAI/Ling-3.0-flash-VL","name":"inclusionAI/Ling-3.0-flash-VL","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.060000000000000005,"output":0.18,"cache_read":0.012000000000000002,"cache_write":null},"org":"inclusionai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":null,"description":"Native multimodal hybrid MoE model for image and video understanding, reasoning, and visual agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://novita.ai/docs/guides/introduction","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.6,"coding_index":57,"agentic_index":28.7,"design_arena_best":null}},{"id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","name":"meta-llama/Llama-4-Scout-17B-16E-Instruct","provider":"deepinfra","quantization":null,"discount":0,"context_length":327680,"pricing":{"input":0.1,"output":0.3,"cache_read":null,"cache_write":null},"org":"meta","max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for long-context analysis and efficient agents","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1321.500615383975,"arena_text_rank":260,"arena_text_rating_lower":1316.763226028046,"arena_text_rating_upper":1326.2380047399038,"arena_text_vote_count":29826,"arena_text_date":"2026-10-15","arena_creative_writing":1288.7981083268853,"arena_creative_writing_rank":252,"arena_creative_writing_rating_lower":1278.6926334652305,"arena_creative_writing_rating_upper":1298.90358318854,"arena_creative_writing_vote_count":3760,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen/Qwen3.5-397B-A17B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.45,"output":2.9999999999999996,"cache_read":0.22000000050000001,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":81920,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.5-397B-A17B","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-15","knowledge_cutoff":"2025-01","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.4,"coding_index":48.2,"agentic_index":8.3,"design_arena_best":{"category":"website","elo":1189,"win_rate":52.5,"rank":70},"arena_text":1441.5655970064536,"arena_text_rank":94,"arena_text_rating_lower":1438.475745273247,"arena_text_rating_upper":1444.6554487396604,"arena_text_vote_count":93567,"arena_text_date":"2026-10-15","arena_creative_writing":1405.830251014268,"arena_creative_writing_rank":100,"arena_creative_writing_rating_lower":1400.1870528811276,"arena_creative_writing_rating_upper":1411.4734491474082,"arena_creative_writing_vote_count":16543,"arena_creative_writing_date":"2026-10-15"}},{"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","name":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","provider":"deepinfra","quantization":null,"discount":0,"context_length":128000,"pricing":{"input":0.075,"output":0.2,"cache_read":null,"cache_write":null},"org":"mistral","open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"microsoft/phi-4","name":"microsoft/phi-4","provider":"deepinfra","quantization":null,"discount":0,"context_length":16384,"pricing":{"input":0.07,"output":0.14,"cache_read":null,"cache_write":null},"org":"microsoft","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-11","knowledge_cutoff":"2023-10","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1256.3106977286461,"arena_text_rank":320,"arena_text_rating_lower":1251.6997685220442,"arena_text_rating_upper":1260.921626935248,"arena_text_vote_count":24126,"arena_text_date":"2026-10-15","arena_creative_writing":1210.0709700014152,"arena_creative_writing_rank":319,"arena_creative_writing_rating_lower":1200.3295738650274,"arena_creative_writing_rating_upper":1219.8123661378029,"arena_creative_writing_vote_count":4062,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-4-31B-it","name":"google/gemma-4-31B-it","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.2,"output":0.4,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"max_completion_tokens":32768,"modelsdev":{"base_url":null,"model_id":"google/gemma-4-31B-it","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"anthropic/claude-sonnet-5","name":"anthropic/claude-sonnet-5","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2.9999999999999996,"output":15,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-29","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.2,"coding_index":71.5,"agentic_index":43.6,"design_arena_best":{"category":"codecategories","elo":1274,"win_rate":52.5,"rank":28},"arena_text":1461.0744345634098,"arena_text_rank":58,"arena_text_rating_lower":1456.948350050117,"arena_text_rating_upper":1465.2005190767027,"arena_text_vote_count":49595,"arena_text_date":"2026-10-15","arena_creative_writing":1435.9673899026286,"arena_creative_writing_rank":64,"arena_creative_writing_rating_lower":1428.9376863536472,"arena_creative_writing_rating_upper":1442.99709345161,"arena_creative_writing_vote_count":10285,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-4-31B-it-turbo","name":"google/gemma-4-31B-it-turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.09,"output":0.33999999999999997,"cache_read":0.050000000399999994,"cache_write":null},"org":"google","open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"anthropic/claude-sonnet-4-6","name":"anthropic/claude-sonnet-4-6","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2.9999999999999996,"output":15,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-17","knowledge_cutoff":"2025-08-31","description":"Claude workhorse for coding agents, careful analysis, and production cost control","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1472.102664549635,"arena_text_rank":45,"arena_text_rating_lower":1468.5893014469252,"arena_text_rating_upper":1475.6160276523447,"arena_text_vote_count":70931,"arena_text_date":"2026-10-15","arena_creative_writing":1449.2383090921242,"arena_creative_writing_rank":40,"arena_creative_writing_rating_lower":1442.7173189840858,"arena_creative_writing_rating_upper":1455.7592992001626,"arena_creative_writing_vote_count":12367,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-3-4b-it","name":"google/gemma-3-4b-it","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.05,"output":0.1,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":null,"model_id":"google/gemma-3-4b-it","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-03-12","knowledge_cutoff":"2024-08","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":2.7,"agentic_index":null,"design_arena_best":null,"arena_text":1303.262118441158,"arena_text_rank":284,"arena_text_rating_lower":1293.945083293274,"arena_text_rating_upper":1312.5791535890423,"arena_text_vote_count":4171,"arena_text_date":"2026-10-15","arena_creative_writing":1274.590709714658,"arena_creative_writing_rank":272,"arena_creative_writing_rating_lower":1252.2953144263392,"arena_creative_writing_rating_upper":1296.8861050029766,"arena_creative_writing_vote_count":666,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-4-26B-A4B-it","name":"google/gemma-4-26B-A4B-it","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.07,"output":0.33999999999999997,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"max_completion_tokens":32768,"modelsdev":{"base_url":null,"model_id":"google/gemma-4-26B-A4B-it","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"Qwen/Qwen3.8-27B","name":"Qwen/Qwen3.8-27B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.2,"output":2.5,"cache_read":0.05,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":32768,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.8-27B","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"tencent/Hy4-preview","name":"tencent/Hy4-preview","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.834,"output":2.5010000000000003,"cache_read":0.04199999814,"cache_write":null},"org":"tencent","zdr":true,"max_completion_tokens":64000,"modelsdev":{"base_url":null,"model_id":"tencent/Hy4-preview","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-28","knowledge_cutoff":null,"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"meta-llama/Llama-Guard-4-12B","name":"meta-llama/Llama-Guard-4-12B","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.18,"output":0.18,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"max_completion_tokens":163840,"modelsdev":{"base_url":null,"model_id":"meta-llama/Llama-Guard-4-12B","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-04-29","knowledge_cutoff":null,"description":"Multimodal Llama 4-based safety classifier for moderating prompts and responses","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Llama 4 Community License","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"deepseek-ai/DeepSeek-V4-Flash-0731","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.060000000000000005,"output":0.18,"cache_read":0.015000000000000001,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":384000,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"zai-org/GLM-5.2","name":"zai-org/GLM-5.2","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.7499999999999999,"output":2.4,"cache_read":0.1400000025,"cache_write":0.9375},"org":"z-ai","zdr":true,"max_completion_tokens":32768,"modelsdev":{"base_url":null,"model_id":"zai-org/GLM-5.2","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"XiaomiMiMo/MiMo-V2.6-Pro","name":"XiaomiMiMo/MiMo-V2.6-Pro","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.43,"output":0.87,"cache_read":0.0035999987000000003,"cache_write":null},"org":"xiaomi","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":null,"model_id":"XiaomiMiMo/MiMo-V2.6-Pro","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":null,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1335,"win_rate":58.4,"rank":7},"arena_text":1479.194755229377,"arena_text_rank":27,"arena_text_rating_lower":1469.827446672319,"arena_text_rating_upper":1488.5620637864351,"arena_text_vote_count":4075,"arena_text_date":"2026-10-15","arena_creative_writing":1444.679173566022,"arena_creative_writing_rank":52,"arena_creative_writing_rating_lower":1423.5979241643079,"arena_creative_writing_rating_upper":1465.760422967736,"arena_creative_writing_vote_count":793,"arena_creative_writing_date":"2026-10-15"}},{"id":"mistralai/Mistral-Small-24B-Instruct-2501","name":"mistralai/Mistral-Small-24B-Instruct-2501","provider":"deepinfra","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":0.05,"output":0.08,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"mistralai/Mistral-Small-24B-Instruct-2501","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-01-30","knowledge_cutoff":"2023-10-31","description":"Efficient Mistral model for fast chat, extraction, and production assistants","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1274.4008385707102,"arena_text_rank":308,"arena_text_rating_lower":1268.4792030976703,"arena_text_rating_upper":1280.3224740437502,"arena_text_vote_count":14681,"arena_text_date":"2026-10-15","arena_creative_writing":1226.673238147182,"arena_creative_writing_rank":310,"arena_creative_writing_rating_lower":1214.2597346551445,"arena_creative_writing_rating_upper":1239.0867416392196,"arena_creative_writing_vote_count":2415,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-3-12b-it","name":"google/gemma-3-12b-it","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.05,"output":0.15,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":null,"model_id":"google/gemma-3-12b-it","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-03-12","knowledge_cutoff":"2024-08","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":5.8,"agentic_index":0.1,"design_arena_best":null,"arena_text":1341.7699741013544,"arena_text_rank":233,"arena_text_rating_lower":1332.2584502580542,"arena_text_rating_upper":1351.2814979446548,"arena_text_vote_count":3829,"arena_text_date":"2026-10-15","arena_creative_writing":1332.6341732820492,"arena_creative_writing_rank":200,"arena_creative_writing_rating_lower":1309.3689418803422,"arena_creative_writing_rating_upper":1355.8994046837565,"arena_creative_writing_vote_count":600,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"deepseek-ai/DeepSeek-V4-Pro","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1.2999999999999998,"output":2.5999999999999996,"cache_read":0.10000000399999999,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4-Pro","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen3.5-27B","name":"Qwen/Qwen3.5-27B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.26,"output":2.5999999999999996,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":65536,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.5-27B","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.9,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1408.6798859866929,"arena_text_rank":153,"arena_text_rating_lower":1404.387434481456,"arena_text_rating_upper":1412.9723374919295,"arena_text_vote_count":28671,"arena_text_date":"2026-10-15","arena_creative_writing":1357.6097049465236,"arena_creative_writing_rank":171,"arena_creative_writing_rating_lower":1348.198921054706,"arena_creative_writing_rating_upper":1367.0204888383412,"arena_creative_writing_vote_count":4298,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen3-30B-A3B","name":"Qwen/Qwen3-30B-A3B","provider":"deepinfra","quantization":null,"discount":0,"context_length":40960,"pricing":{"input":0.12000000000000001,"output":0.5,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3-30B-A3B","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-04-28","knowledge_cutoff":null,"description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":967,"win_rate":39,"rank":121},"arena_text":1326.720438450228,"arena_text_rank":250,"arena_text_rating_lower":1321.9721027866842,"arena_text_rating_upper":1331.4687741137718,"arena_text_vote_count":26157,"arena_text_date":"2026-10-15","arena_creative_writing":1283.6416183810823,"arena_creative_writing_rank":260,"arena_creative_writing_rating_lower":1273.1820766690896,"arena_creative_writing_rating_upper":1294.1011600930747,"arena_creative_writing_vote_count":3340,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.2,"output":0.6,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":384000,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"anthropic/claude-haiku-4-5","name":"anthropic/claude-haiku-4-5","provider":"deepinfra","quantization":null,"discount":0,"context_length":200000,"pricing":{"input":1,"output":5,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-15","knowledge_cutoff":"2025-02-28","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1414.264434778655,"arena_text_rank":144,"arena_text_rating_lower":1411.8605435448783,"arena_text_rating_upper":1416.6683260124319,"arena_text_vote_count":149199,"arena_text_date":"2026-10-15","arena_creative_writing":1387.6018446360315,"arena_creative_writing_rank":135,"arena_creative_writing_rating_lower":1382.8941526581261,"arena_creative_writing_rating_upper":1392.3095366139369,"arena_creative_writing_vote_count":25394,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4-8","name":"anthropic/claude-opus-4-8","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":5,"output":25,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-28","knowledge_cutoff":"2026-01","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.3188347223909,"arena_text_rank":40,"arena_text_rating_lower":1470.4723897525055,"arena_text_rating_upper":1478.1652796922765,"arena_text_vote_count":65172,"arena_text_date":"2026-10-15","arena_creative_writing":1462.8968823288687,"arena_creative_writing_rank":26,"arena_creative_writing_rating_lower":1456.397399182796,"arena_creative_writing_rating_upper":1469.3963654749414,"arena_creative_writing_vote_count":12829,"arena_creative_writing_date":"2026-10-15"}},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning","name":"nvidia/NVIDIA-Nemotron-3.5-Lightning","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.060000000000000005,"output":0.16,"cache_read":0.030000000000000002,"cache_write":null},"org":"nvidia","open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":26.8,"agentic_index":3.5,"design_arena_best":null}},{"id":"ByteDance/Seed-2.0-mini","name":"ByteDance/Seed-2.0-mini","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.1,"output":0.4,"cache_read":0.020000000000000004,"cache_write":null},"org":"bytedance","max_completion_tokens":32000,"context_price_tiers":[{"above_tokens":128000,"input":0.2,"output":0.8,"cache_read":0.2,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"ByteDance/Seed-2.0-mini","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-14","knowledge_cutoff":null,"description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"lifecycle_status":null},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","name":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.5,"output":2.2,"cache_read":0.1,"cache_write":null},"org":"nvidia","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-04","knowledge_cutoff":"2025-09","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.8,"coding_index":49.3,"agentic_index":20.1,"design_arena_best":{"category":"codecategories","elo":1146,"win_rate":36,"rank":89},"arena_text":1426.020838970455,"arena_text_rank":121,"arena_text_rating_lower":1419.1357703185906,"arena_text_rating_upper":1432.9059076223198,"arena_text_vote_count":11567,"arena_text_date":"2026-10-15","arena_creative_writing":1381.8887162114006,"arena_creative_writing_rank":142,"arena_creative_writing_rating_lower":1368.4266147995731,"arena_creative_writing_rating_upper":1395.3508176232283,"arena_creative_writing_vote_count":2189,"arena_creative_writing_date":"2026-10-15"}},{"id":"ByteDance/Seed-2.0-pro","name":"ByteDance/Seed-2.0-pro","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.5,"output":2.9999999999999996,"cache_read":0.1,"cache_write":null},"org":"bytedance","max_completion_tokens":128000,"context_price_tiers":[{"above_tokens":128000,"input":1,"output":6,"cache_read":0.2,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"ByteDance/Seed-2.0-pro","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-14","knowledge_cutoff":null,"description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"lifecycle_status":null},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","name":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.3,"output":1,"cache_read":0.09999999899999999,"cache_write":null},"org":"qwen","max_completion_tokens":66536,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-07-22","knowledge_cutoff":"2025-04","description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.9,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1387.5520617800003,"arena_text_rank":180,"arena_text_rating_lower":1382.5746531348318,"arena_text_rating_upper":1392.5294704251687,"arena_text_vote_count":25195,"arena_text_date":"2026-10-15","arena_creative_writing":1362.3482460581613,"arena_creative_writing_rank":167,"arena_creative_writing_rating_lower":1351.635511889283,"arena_creative_writing_rating_upper":1373.0609802270394,"arena_creative_writing_vote_count":3239,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen/Qwen2.5-72B-Instruct","provider":"deepinfra","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":0.36,"output":0.4,"cache_read":null,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-09-18","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":7.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1302.8538323153166,"arena_text_rank":285,"arena_text_rating_lower":1298.7656146877564,"arena_text_rating_upper":1306.942049942877,"arena_text_vote_count":39406,"arena_text_date":"2026-10-15","arena_creative_writing":1254.1391200604678,"arena_creative_writing_rank":294,"arena_creative_writing_rating_lower":1245.6487667909996,"arena_creative_writing_rating_upper":1262.6294733299362,"arena_creative_writing_vote_count":5684,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-ai/DeepSeek-V3.2","name":"deepseek-ai/DeepSeek-V3.2","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.26,"output":0.38,"cache_read":0.13,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":64000,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V3.2","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-models/Muse-Glimmer-30B","name":"meta-models/Muse-Glimmer-30B","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.3,"output":1.2,"cache_read":0.039999999,"cache_write":null},"org":"meta-models","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":"Apache 2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.3,"coding_index":49,"agentic_index":8.5,"design_arena_best":{"category":"uicomponent","elo":1206,"win_rate":40,"rank":58}}},{"id":"mistralai/Mistral-Nemo-Instruct-2407","name":"mistralai/Mistral-Nemo-Instruct-2407","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.029,"output":0.030000000000000002,"cache_read":null,"cache_write":null},"org":"mistral","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-07-18","knowledge_cutoff":"2024-05","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"ByteDance/Seed-1.8","name":"ByteDance/Seed-1.8","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.25,"output":2,"cache_read":0.05,"cache_write":null},"org":"bytedance","open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"anthropic/claude-opus-5-5","name":"anthropic/claude-opus-5-5","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":4,"output":20,"cache_read":0.2,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":"2026-06","description":"Claude model for long-running agentic coding and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","name":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.08499999999999999,"output":0.4,"cache_read":null,"cache_write":null},"org":"nvidia","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-11","knowledge_cutoff":"2025-06","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.8,"coding_index":37.7,"agentic_index":1.7,"design_arena_best":null,"arena_text":1360.080568965112,"arena_text_rank":206,"arena_text_rating_lower":1352.9580190563502,"arena_text_rating_upper":1367.2031188738738,"arena_text_vote_count":7878,"arena_text_date":"2026-10-15","arena_creative_writing":1303.567788198394,"arena_creative_writing_rank":234,"arena_creative_writing_rating_lower":1285.8236973217145,"arena_creative_writing_rating_upper":1321.3118790750734,"arena_creative_writing_vote_count":1121,"arena_creative_writing_date":"2026-10-15"}},{"id":"zai-org/GLM-4.6","name":"zai-org/GLM-4.6","provider":"deepinfra","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":0.5,"output":2,"cache_read":0.1,"cache_write":null},"org":"z-ai","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":null,"model_id":"zai-org/GLM-4.6","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-09-30","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":14.9,"coding_index":45.8,"agentic_index":null,"design_arena_best":{"category":"godotgamedev","elo":1180,"win_rate":53.2,"rank":17},"arena_text":1424.1228406450284,"arena_text_rank":125,"arena_text_rating_lower":1420.2224633968601,"arena_text_rating_upper":1428.0232178931967,"arena_text_vote_count":35824,"arena_text_date":"2026-10-15","arena_creative_writing":1400.5550945178709,"arena_creative_writing_rank":109,"arena_creative_writing_rating_lower":1392.044388175411,"arena_creative_writing_rating_upper":1409.0658008603307,"arena_creative_writing_vote_count":5145,"arena_creative_writing_date":"2026-10-15"}},{"id":"nvidia/Nemotron-Content-Safety-3.5","name":"nvidia/Nemotron-Content-Safety-3.5","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.2,"output":0.2,"cache_read":null,"cache_write":null},"org":"nvidia","open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"ByteDance/Seed-2.0-code","name":"ByteDance/Seed-2.0-code","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.5,"output":2.9999999999999996,"cache_read":0.1,"cache_write":null},"org":"bytedance","max_completion_tokens":131072,"context_price_tiers":[{"above_tokens":128000,"input":1,"output":6,"cache_read":0.2,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"ByteDance/Seed-2.0-code","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-14","knowledge_cutoff":null,"description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"lifecycle_status":null},{"id":"google/gemini-3.1-pro","name":"google/gemini-3.1-pro","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2,"output":11.999999999999998,"cache_read":null,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-19","knowledge_cutoff":"2025-01","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://ai.google.dev/gemini-api/docs/models","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.7,"coding_index":68.8,"agentic_index":8.2,"design_arena_best":{"category":"svg","elo":1283,"win_rate":67.8,"rank":12},"arena_text":1486.9094358879568,"arena_text_rank":19,"arena_text_rating_lower":1483.9491002818586,"arena_text_rating_upper":1489.869771494055,"arena_text_vote_count":127649,"arena_text_date":"2026-10-15","arena_creative_writing":1480.996930948638,"arena_creative_writing_rank":12,"arena_creative_writing_rating_lower":1475.677482894711,"arena_creative_writing_rating_upper":1486.3163790025653,"arena_creative_writing_vote_count":23619,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","name":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.02,"output":0.04,"cache_read":null,"cache_write":null},"org":"meta","open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":5.4,"agentic_index":null,"design_arena_best":null,"arena_text":1211.2299856226907,"arena_text_rank":343,"arena_text_rating_lower":1207.0682111539336,"arena_text_rating_upper":1215.3917600914476,"arena_text_vote_count":49605,"arena_text_date":"2026-10-15","arena_creative_writing":1177.0939803061635,"arena_creative_writing_rank":342,"arena_creative_writing_rating_lower":1168.6099028263632,"arena_creative_writing_rating_upper":1185.5780577859637,"arena_creative_writing_vote_count":7346,"arena_creative_writing_date":"2026-10-15"}},{"id":"inclusionAI/Ling-3.1-flash","name":"inclusionAI/Ling-3.1-flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.3,"output":0.9,"cache_read":0.06,"cache_write":null},"org":"inclusionai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-29","knowledge_cutoff":null,"description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://novita.ai/docs/guides/introduction","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.1,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen/Qwen3-VL-235B-A22B-Instruct","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.2,"output":0.8799999999999999,"cache_read":0.11000000000000001,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":32768,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-09-23","knowledge_cutoff":"2025-03-31","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1413.3151783944136,"arena_text_rank":146,"arena_text_rating_lower":1406.7915427149521,"arena_text_rating_upper":1419.8388140738748,"arena_text_vote_count":11320,"arena_text_date":"2026-10-15","arena_creative_writing":1356.5721800790488,"arena_creative_writing_rank":172,"arena_creative_writing_rating_lower":1339.6991843255719,"arena_creative_writing_rating_upper":1373.4451758325256,"arena_creative_writing_vote_count":1356,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen/Qwen3-VL-30B-A3B-Instruct","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":32768,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-10-04","knowledge_cutoff":null,"description":"Open vision-language MoE model for image and video understanding, documents, and visual agents","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":7.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"Qwen/Qwen3.8-Max","name":"Qwen/Qwen3.8-Max","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":1.6500000000000001,"output":4.9510000000000005,"cache_read":0.20599999200000002,"cache_write":null},"org":"qwen","max_completion_tokens":131072,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.8-Max","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-03","knowledge_cutoff":null,"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":45.4,"coding_index":76.2,"agentic_index":56,"design_arena_best":null,"arena_text":1482.3530183862679,"arena_text_rank":24,"arena_text_rating_lower":1477.3762943638942,"arena_text_rating_upper":1487.3297424086413,"arena_text_vote_count":27766,"arena_text_date":"2026-10-15","arena_creative_writing":1468.9997777918718,"arena_creative_writing_rank":19,"arena_creative_writing_rating_lower":1459.9936527553632,"arena_creative_writing_rating_upper":1478.0059028283804,"arena_creative_writing_vote_count":5471,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-3-27b-it","name":"google/gemma-3-27b-it","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.08,"output":0.16,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":null,"model_id":"google/gemma-3-27b-it","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-03-12","knowledge_cutoff":"2024-08","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":10.1,"agentic_index":0.1,"design_arena_best":null,"arena_text":1365.4528659816333,"arena_text_rank":200,"arena_text_rating_lower":1361.7493134028653,"arena_text_rating_upper":1369.1564185604013,"arena_text_vote_count":46666,"arena_text_date":"2026-10-15","arena_creative_writing":1348.3838436543454,"arena_creative_writing_rank":182,"arena_creative_writing_rating_lower":1340.6538455393713,"arena_creative_writing_rating_upper":1356.1138417693194,"arena_creative_writing_vote_count":6308,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4-7","name":"anthropic/claude-opus-4-7","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":5,"output":25,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-14","knowledge_cutoff":"2026-01-31","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMaxAI/MiniMax-M3","provider":"deepinfra","quantization":null,"discount":0,"context_length":524288,"pricing":{"input":0.28,"output":1.1,"cache_read":0.05600000000000001,"cache_write":null},"org":"minimax","zdr":true,"max_completion_tokens":512000,"modelsdev":{"base_url":null,"model_id":"MiniMaxAI/MiniMax-M3","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-06-01","knowledge_cutoff":null,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-ai/DeepSeek-V3","name":"deepseek-ai/DeepSeek-V3","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.32,"output":0.8899999999999999,"cache_read":null,"cache_write":null},"org":"deepseek","max_completion_tokens":8192,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V3","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2024-12-26","knowledge_cutoff":null,"description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"DeepSeek Model License","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":8.5,"coding_index":23,"agentic_index":0.8,"design_arena_best":null,"arena_text":1358.4093056127422,"arena_text_rank":208,"arena_text_rating_lower":1353.6507156986147,"arena_text_rating_upper":1363.1678955268694,"arena_text_vote_count":21770,"arena_text_date":"2026-10-15","arena_creative_writing":1348.5157528819225,"arena_creative_writing_rank":181,"arena_creative_writing_rating_lower":1338.4412380127264,"arena_creative_writing_rating_upper":1358.5902677511187,"arena_creative_writing_vote_count":3623,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"deepseek-ai/DeepSeek-V4.1-Flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.2,"output":0.6,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":384000,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4.1-Flash","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-ai/DeepSeek-R1-0528","name":"deepseek-ai/DeepSeek-R1-0528","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.5,"output":2.15,"cache_read":0.35,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":64000,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-R1-0528","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-05-28","knowledge_cutoff":"2024-07","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1182,"win_rate":60.9,"rank":65},"arena_text":1421.4290222328934,"arena_text_rank":130,"arena_text_rating_lower":1415.7507882696264,"arena_text_rating_upper":1427.1072561961605,"arena_text_vote_count":18167,"arena_text_date":"2026-10-15","arena_creative_writing":1388.8970764882217,"arena_creative_writing_rank":132,"arena_creative_writing_rating_lower":1376.3501553215542,"arena_creative_writing_rating_upper":1401.4439976548892,"arena_creative_writing_vote_count":2408,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.5-flash","name":"google/gemini-3.5-flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.4999999999999998,"output":9,"cache_read":null,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-19","knowledge_cutoff":"2025-01","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://ai.google.dev/gemini-api/docs/models","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":32.6,"coding_index":70.1,"agentic_index":26,"design_arena_best":{"category":"uicomponent","elo":1267,"win_rate":54.1,"rank":32}}},{"id":"moonshotai/Kimi-K3","name":"moonshotai/Kimi-K3","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":2.8499999999999996,"output":14.25,"cache_read":0.285,"cache_write":3.5625},"org":"moonshot","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":null,"model_id":"moonshotai/Kimi-K3","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"Sao10K/L3-8B-Lunaris-v1-Turbo","name":"Sao10K/L3-8B-Lunaris-v1-Turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":8192,"pricing":{"input":0.04,"output":0.05,"cache_read":null,"cache_write":null},"org":"sao10k","open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"google/gemini-2.5-flash","name":"google/gemini-2.5-flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.3,"output":2.5,"cache_read":null,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://ai.google.dev/gemini-api/docs/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1134,"win_rate":49.1,"rank":90},"arena_text":1409.2369734409983,"arena_text_rank":151,"arena_text_rating_lower":1406.7997377325987,"arena_text_rating_upper":1411.6742091493982,"arena_text_vote_count":125521,"arena_text_date":"2026-10-15","arena_creative_writing":1393.8601283158314,"arena_creative_writing_rank":118,"arena_creative_writing_rating_lower":1388.8719634210272,"arena_creative_writing_rating_upper":1398.8482932106353,"arena_creative_writing_vote_count":17664,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen3-14B","name":"Qwen/Qwen3-14B","provider":"deepinfra","quantization":null,"discount":0,"context_length":40960,"pricing":{"input":0.12000000000000001,"output":0.24000000000000002,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":13.8,"agentic_index":0.9,"design_arena_best":null}},{"id":"ibm-granite/granite-4.2-8b","name":"ibm-granite/granite-4.2-8b","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.060000000000000005,"output":0.25,"cache_read":0.015000000000000001,"cache_write":null},"org":"ibm","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-25","knowledge_cutoff":null,"description":"Granite 4.2 8B is an instruct model capable of enhanced tool calling, instruction following, and chat capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.1,"coding_index":22.4,"agentic_index":1.3,"design_arena_best":null,"arena_text":1290.1761926441807,"arena_text_rank":290,"arena_text_rating_lower":1279.0036546892693,"arena_text_rating_upper":1301.3487305990918,"arena_text_vote_count":3254,"arena_text_date":"2026-10-15","arena_creative_writing":1200.7601919979436,"arena_creative_writing_rank":325,"arena_creative_writing_rating_lower":1173.755372152443,"arena_creative_writing_rating_upper":1227.765011843444,"arena_creative_writing_vote_count":628,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen/Qwen3.6-35B-A3B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.1,"output":0.95,"cache_read":0.1,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":81920,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.6-35B-A3B","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"openai/gpt-oss-20b","name":"openai/gpt-oss-20b","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.030000000000000002,"output":0.14,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-20b","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen3.5-9B","name":"Qwen/Qwen3.5-9B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.1,"output":0.15,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":65536,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.5-9B","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.2,"coding_index":28.7,"agentic_index":1.2,"design_arena_best":null}},{"id":"thinkingmachines/Inkling-Small","name":"thinkingmachines/Inkling-Small","provider":"deepinfra","quantization":null,"discount":0,"context_length":524288,"pricing":{"input":0.45,"output":1.2,"cache_read":0.099999999,"cache_write":null},"org":"thinkingmachines","zdr":true,"max_completion_tokens":1048576,"modelsdev":{"base_url":null,"model_id":"thinkingmachines/Inkling-Small","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-07-30","knowledge_cutoff":null,"description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.9,"coding_index":52.9,"agentic_index":23.5,"design_arena_best":null,"arena_text":1403.9804130510786,"arena_text_rank":156,"arena_text_rating_lower":1399.3141720479516,"arena_text_rating_upper":1408.6466540542056,"arena_text_vote_count":32304,"arena_text_date":"2026-10-15","arena_creative_writing":1313.687203080526,"arena_creative_writing_rank":218,"arena_creative_writing_rating_lower":1305.2979782995662,"arena_creative_writing_rating_upper":1322.0764278614859,"arena_creative_writing_vote_count":6963,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-4-31B-it-Ultra","name":"google/gemma-4-31B-it-Ultra","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.27,"output":0.76,"cache_read":null,"cache_write":null},"org":"google","open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-ai/DeepSeek-V3.1","name":"deepseek-ai/DeepSeek-V3.1","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.25,"output":0.95,"cache_read":0.13,"cache_write":null},"org":"deepseek","max_completion_tokens":8192,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V3.1","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-08-21","knowledge_cutoff":null,"description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1417.0286131400032,"arena_text_rank":135,"arena_text_rating_lower":1410.9662146935234,"arena_text_rating_upper":1423.0910115864833,"arena_text_vote_count":14610,"arena_text_date":"2026-10-15","arena_creative_writing":1387.9765537688254,"arena_creative_writing_rank":134,"arena_creative_writing_rating_lower":1374.5186597419859,"arena_creative_writing_rating_upper":1401.4344477956652,"arena_creative_writing_vote_count":1978,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen/Qwen3-Next-80B-A3B-Instruct","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.09,"output":1.1,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":32768,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-09","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.6,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1398.5312003749314,"arena_text_rank":164,"arena_text_rating_lower":1393.7574764680655,"arena_text_rating_upper":1403.3049242817972,"arena_text_vote_count":22760,"arena_text_date":"2026-10-15","arena_creative_writing":1313.3902317801694,"arena_creative_writing_rank":219,"arena_creative_writing_rating_lower":1302.5039488652117,"arena_creative_writing_rating_upper":1324.2765146951272,"arena_creative_writing_vote_count":3033,"arena_creative_writing_date":"2026-10-15"}},{"id":"zai-org/GLM-5.3-Flash","name":"zai-org/GLM-5.3-Flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":null,"model_id":"zai-org/GLM-5.3-Flash","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-5","name":"anthropic/claude-opus-5","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":5,"output":25,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-24","knowledge_cutoff":"2026-05","description":"Strongest Claude Opus model for coding, agents, and professional work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.8,"coding_index":78,"agentic_index":56.5,"design_arena_best":{"category":"asciiart","elo":1358,"win_rate":68.9,"rank":1}}},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"deepseek-ai/DeepSeek-V4-Flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.09,"output":0.18,"cache_read":0.018,"cache_write":0.1125},"org":"deepseek","zdr":true,"max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4-Flash","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen/Qwen3-235B-A22B-Instruct-2507","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.09,"output":0.55,"cache_read":null,"cache_write":null},"org":"qwen","max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-07-21","knowledge_cutoff":null,"description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Apache 2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1422.131004335956,"arena_text_rank":128,"arena_text_rating_lower":1419.580313231772,"arena_text_rating_upper":1424.6816954401404,"arena_text_vote_count":98134,"arena_text_date":"2026-10-15","arena_creative_writing":1378.4430397696394,"arena_creative_writing_rank":146,"arena_creative_writing_rating_lower":1373.0020337042083,"arena_creative_writing_rating_upper":1383.8840458350703,"arena_creative_writing_vote_count":13895,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b-Ultra","name":"openai/gpt-oss-120b-Ultra","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.2,"output":0.95,"cache_read":null,"cache_write":null},"org":"openai","open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"Qwen/Qwen3-32B","name":"Qwen/Qwen3-32B","provider":"deepinfra","quantization":null,"discount":0,"context_length":40960,"pricing":{"input":0.08,"output":0.28,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3-32B","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-04-28","knowledge_cutoff":"2025-04","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":15.3,"agentic_index":0.9,"design_arena_best":null,"arena_text":1346.8054887198539,"arena_text_rank":223,"arena_text_rating_lower":1337.3482173985908,"arena_text_rating_upper":1356.2627600411167,"arena_text_vote_count":3926,"arena_text_date":"2026-10-15","arena_creative_writing":1303.7112252714267,"arena_creative_writing_rank":233,"arena_creative_writing_rating_lower":1281.09210485787,"arena_creative_writing_rating_upper":1326.330345684983,"arena_creative_writing_vote_count":616,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.1-flash-lite","name":"google/gemini-3.1-flash-lite","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.25,"output":1.4999999999999998,"cache_read":null,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-07","knowledge_cutoff":"2025-01","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://ai.google.dev/gemini-api/docs/models","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":15.6,"coding_index":34.7,"agentic_index":1.6,"design_arena_best":{"category":"asciiart","elo":1164,"win_rate":50.8,"rank":33},"arena_text":1432.9270943558301,"arena_text_rank":110,"arena_text_rating_lower":1429.3054802422857,"arena_text_rating_upper":1436.5487084693743,"arena_text_vote_count":64211,"arena_text_date":"2026-10-15","arena_creative_writing":1414.317968777435,"arena_creative_writing_rank":89,"arena_creative_writing_rating_lower":1407.4610934144926,"arena_creative_writing_rating_upper":1421.1748441403774,"arena_creative_writing_vote_count":10600,"arena_creative_writing_date":"2026-10-15"}},{"id":"zai-org/GLM-5.3","name":"zai-org/GLM-5.3","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.9,"output":4,"cache_read":0.199999998,"cache_write":null},"org":"z-ai","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":null,"model_id":"zai-org/GLM-5.3","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5-5","name":"anthropic/claude-sonnet-5-5","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2,"output":10,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-28","knowledge_cutoff":"2026-06","description":"Fast Claude model for everyday coding, agents, and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"XiaomiMiMo/MiMo-V2.6-Flash","name":"XiaomiMiMo/MiMo-V2.6-Flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028000000000000004,"cache_write":null},"org":"xiaomi","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":null,"model_id":"XiaomiMiMo/MiMo-V2.6-Flash","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen3.6-27B","name":"Qwen/Qwen3.6-27B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.32,"output":3.2,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":65536,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.6-27B","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":21.4,"coding_index":53.7,"agentic_index":18.5,"design_arena_best":null}},{"id":"Sao10K/L3.1-70B-Euryale-v2.2","name":"Sao10K/L3.1-70B-Euryale-v2.2","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.85,"output":0.85,"cache_read":null,"cache_write":null},"org":"sao10k","open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"Qwen/Qwen3.7-Max","name":"Qwen/Qwen3.7-Max","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":null},"org":"qwen","max_completion_tokens":131072,"context_price_tiers":[{"above_tokens":32000,"input":5,"output":15,"cache_read":1,"cache_write":null},{"above_tokens":128000,"input":6.25,"output":18.5,"cache_read":1.25,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.7-Max","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-05-21","knowledge_cutoff":null,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.5,"coding_index":66,"agentic_index":22.5,"design_arena_best":{"category":"dataviz","elo":1276,"win_rate":53,"rank":24},"arena_text":1474.346453572102,"arena_text_rank":39,"arena_text_rating_lower":1464.6199672413577,"arena_text_rating_upper":1484.0729399028464,"arena_text_vote_count":3934,"arena_text_date":"2026-10-15","arena_creative_writing":1439.2456129096304,"arena_creative_writing_rank":60,"arena_creative_writing_rating_lower":1411.9628845744933,"arena_creative_writing_rating_upper":1466.5283412447675,"arena_creative_writing_vote_count":508,"arena_creative_writing_date":"2026-10-15"}},{"id":"zai-org/GLM-4.7","name":"zai-org/GLM-4.7","provider":"deepinfra","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":0.4,"output":1.75,"cache_read":0.08000000000000002,"cache_write":null},"org":"z-ai","zdr":true,"max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"zai-org/GLM-4.7","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.2,"coding_index":45.3,"agentic_index":null,"design_arena_best":{"category":"website","elo":1224,"win_rate":55.3,"rank":57},"arena_text":1441.3266291777354,"arena_text_rank":95,"arena_text_rating_lower":1435.2694154856003,"arena_text_rating_upper":1447.3838428698703,"arena_text_vote_count":12253,"arena_text_date":"2026-10-15","arena_creative_writing":1404.7365646711344,"arena_creative_writing_rank":102,"arena_creative_writing_rating_lower":1391.4905429408939,"arena_creative_writing_rating_upper":1417.9825864013746,"arena_creative_writing_vote_count":1960,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-2.5-pro","name":"google/gemini-2.5-pro","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.25,"output":10,"cache_read":null,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Google's proven reasoning model for coding, math, and multimodal analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://ai.google.dev/gemini-api/docs/models","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16.1,"coding_index":33.3,"agentic_index":1.6,"design_arena_best":{"category":"dataviz","elo":1222,"win_rate":68.2,"rank":51},"arena_text":1445.413742345976,"arena_text_rank":87,"arena_text_rating_lower":1442.9529937841278,"arena_text_rating_upper":1447.8744909078243,"arena_text_vote_count":125366,"arena_text_date":"2026-10-15","arena_creative_writing":1443.1136532706141,"arena_creative_writing_rank":54,"arena_creative_writing_rating_lower":1437.9911660829816,"arena_creative_writing_rating_upper":1448.2361404582468,"arena_creative_writing_vote_count":17694,"arena_creative_writing_date":"2026-10-15"}},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","name":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.15,"output":0.5,"cache_read":0.0199999995,"cache_write":null},"org":"nvidia","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-15","knowledge_cutoff":null,"description":"NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.together.ai/docs/serverless-models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1169,"win_rate":35.2,"rank":82}}},{"id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","name":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.43999999999999995,"output":1.32,"cache_read":0.013999999199999998,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":384000,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-21","knowledge_cutoff":null,"description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":65,"agentic_index":47.5,"design_arena_best":null}},{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen/Qwen3.5-35B-A3B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.14,"output":1,"cache_read":0.05000000040000001,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":81920,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.5-35B-A3B","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":"2025-01","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":19.3,"coding_index":37,"agentic_index":null,"design_arena_best":null,"arena_text":1394.0126320493666,"arena_text_rank":169,"arena_text_rating_lower":1389.7806525536546,"arena_text_rating_upper":1398.2446115450787,"arena_text_vote_count":30457,"arena_text_date":"2026-10-15","arena_creative_writing":1342.8347817996469,"arena_creative_writing_rank":189,"arena_creative_writing_rating_lower":1333.8293445758327,"arena_creative_writing_rating_upper":1351.840219023461,"arena_creative_writing_vote_count":4680,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen/Qwen3.8-Flash","name":"Qwen/Qwen3.8-Flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.113,"output":0.382,"cache_read":0.01409999988,"cache_write":null},"org":"qwen","max_completion_tokens":131072,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.8-Flash","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"inclusionAI/Ling-3.0-flash","name":"inclusionAI/Ling-3.0-flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.060000000000000005,"output":0.18,"cache_read":0.012000000000000002,"cache_write":null},"org":"inclusionai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-23","knowledge_cutoff":null,"description":"Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://novita.ai/docs/guides/introduction","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":50.6,"agentic_index":19.3,"design_arena_best":null}},{"id":"moonshotai/Kimi-K2.6","name":"moonshotai/Kimi-K2.6","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.7499999999999999,"output":3.5,"cache_read":0.15,"cache_write":null},"org":"moonshot","zdr":true,"max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"moonshotai/Kimi-K2.6","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-fable-5","name":"anthropic/claude-fable-5","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":10,"output":50,"cache_read":null,"cache_write":null},"org":"anthropic","max_completion_tokens":128000,"modelsdev":{"base_url":null,"model_id":"anthropic/claude-fable-5","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2026-06-09","knowledge_cutoff":"2026-01-31","description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.6,"coding_index":76.5,"agentic_index":50.7,"design_arena_best":{"category":"gamedev","elo":1335,"win_rate":60.8,"rank":11},"arena_text":1503.6013443401307,"arena_text_rank":4,"arena_text_rating_lower":1499.3137424347174,"arena_text_rating_upper":1507.888946245544,"arena_text_vote_count":42004,"arena_text_date":"2026-10-15","arena_creative_writing":1501.3084222192924,"arena_creative_writing_rank":3,"arena_creative_writing_rating_lower":1493.9313686628855,"arena_creative_writing_rating_upper":1508.6854757756996,"arena_creative_writing_vote_count":9020,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","name":"meta-llama/Llama-3.3-70B-Instruct-Turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.1,"output":0.32,"cache_read":null,"cache_write":null},"org":"meta","max_completion_tokens":16384,"modelsdev":{"base_url":null,"model_id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","doc_url":"https://deepinfra.com/models","confidence":"high","source":"models.dev","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Compact Llama instruction model for fast chat and local deployment","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null,"design_arena_best":null,"arena_text":1318.0654473917496,"arena_text_rank":264,"arena_text_rating_lower":1314.561524832038,"arena_text_rating_upper":1321.569369951461,"arena_text_vote_count":54497,"arena_text_date":"2026-10-15","arena_creative_writing":1285.365717788876,"arena_creative_writing_rank":257,"arena_creative_writing_rating_lower":1278.3092286350516,"arena_creative_writing_rating_upper":1292.4222069427008,"arena_creative_writing_vote_count":8046,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.7-flash","name":"google/gemini-3.7-flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.7499999999999999,"output":3.75,"cache_read":null,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":"2026-03","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://ai.google.dev/gemini-api/docs/models","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.1,"coding_index":76.1,"agentic_index":35.2,"design_arena_best":{"category":"dataviz","elo":1318,"win_rate":55.4,"rank":11},"arena_text":1487.5878753892953,"arena_text_rank":17,"arena_text_rating_lower":1482.7056648473051,"arena_text_rating_upper":1492.4700859312854,"arena_text_vote_count":27232,"arena_text_date":"2026-10-15","arena_creative_writing":1490.973144146456,"arena_creative_writing_rank":5,"arena_creative_writing_rating_lower":1482.129415167425,"arena_creative_writing_rating_upper":1499.816873125487,"arena_creative_writing_vote_count":6003,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3","name":"GLM-5.3","provider":"ember","quantization":null,"discount":0,"context_length":1310720,"pricing":{"input":0.756,"output":2.3760000000000003,"cache_read":0.14040000000000002,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","provider":"ember","quantization":null,"discount":0,"context_length":1310720,"pricing":{"input":0.135,"output":0.44999999999999996,"cache_read":0.045,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.2","name":"GLM-5.2","provider":"ember","quantization":null,"discount":0,"context_length":203000,"pricing":{"input":1.26,"output":3.9600000000000004,"cache_read":0.234,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.1","name":"GLM-5.1","provider":"ember","quantization":null,"discount":0,"context_length":203000,"pricing":{"input":0.9309999999999999,"output":2.926,"cache_read":0.1729,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5","name":"GLM-5","provider":"ember","quantization":null,"discount":0,"context_length":203000,"pricing":{"input":0.5700000000000001,"output":1.824,"cache_read":0.114,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-4.7","name":"GLM-4.7","provider":"ember","quantization":null,"discount":0,"context_length":200000,"pricing":{"input":0.38,"output":1.6624999999999999,"cache_read":0.07600000000000001,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.2,"coding_index":45.3,"agentic_index":null,"design_arena_best":{"category":"website","elo":1224,"win_rate":55.3,"rank":57},"arena_text":1441.3266291777354,"arena_text_rank":95,"arena_text_rating_lower":1435.2694154856003,"arena_text_rating_upper":1447.3838428698703,"arena_text_vote_count":12253,"arena_text_date":"2026-10-15","arena_creative_writing":1404.7365646711344,"arena_creative_writing_rank":102,"arena_creative_writing_rating_lower":1391.4905429408939,"arena_creative_writing_rating_upper":1417.9825864013746,"arena_creative_writing_vote_count":1960,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-4.7-flash","name":"GLM-4.7 Flash","provider":"ember","quantization":null,"discount":0,"context_length":200000,"pricing":{"input":0.057,"output":0.38,"cache_read":0.009500000000000001,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-19","knowledge_cutoff":"2025-04","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://developers.cloudflare.com/workers-ai/models/","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":14.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1202,"win_rate":57.6,"rank":60},"arena_text":1364.5160203965402,"arena_text_rank":201,"arena_text_rating_lower":1358.8016752228536,"arena_text_rating_upper":1370.230365570227,"arena_text_vote_count":12021,"arena_text_date":"2026-10-15","arena_creative_writing":1304.7675155862905,"arena_creative_writing_rank":230,"arena_creative_writing_rating_lower":1291.0131953224686,"arena_creative_writing_rating_upper":1318.5218358501124,"arena_creative_writing_vote_count":1873,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-4.6","name":"GLM-4.6","provider":"ember","quantization":null,"discount":0,"context_length":200000,"pricing":{"input":0.38,"output":1.55,"cache_read":0.07,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-30","knowledge_cutoff":"2024-10","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence","reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":14.9,"coding_index":45.8,"agentic_index":null,"design_arena_best":{"category":"godotgamedev","elo":1180,"win_rate":53.2,"rank":17},"arena_text":1424.1228406450284,"arena_text_rank":125,"arena_text_rating_lower":1420.2224633968601,"arena_text_rating_upper":1428.0232178931967,"arena_text_vote_count":35824,"arena_text_date":"2026-10-15","arena_creative_writing":1400.5550945178709,"arena_creative_writing_rank":109,"arena_creative_writing_rating_lower":1392.044388175411,"arena_creative_writing_rating_upper":1409.0658008603307,"arena_creative_writing_vote_count":5145,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-4.5","name":"GLM-4.5","provider":"ember","quantization":null,"discount":0,"context_length":131000,"pricing":{"input":0.5700000000000001,"output":2.09,"cache_read":0.10450000000000001,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-28","knowledge_cutoff":"2025-04","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.z.ai/guides/overview/pricing","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1168,"win_rate":53.7,"rank":83},"arena_text":1410.7960767851844,"arena_text_rank":150,"arena_text_rating_lower":1405.8737096155037,"arena_text_rating_upper":1415.7184439548648,"arena_text_vote_count":23796,"arena_text_date":"2026-10-15","arena_creative_writing":1372.2591640865946,"arena_creative_writing_rank":155,"arena_creative_writing_rating_lower":1361.3157066060623,"arena_creative_writing_rating_upper":1383.2026215671272,"arena_creative_writing_vote_count":3093,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-4.5-air","name":"GLM-4.5 Air","provider":"ember","quantization":null,"discount":0,"context_length":131000,"pricing":{"input":0.12349999999999998,"output":0.8075,"cache_read":0.02375,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-28","knowledge_cutoff":"2025-04","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.1,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1186,"win_rate":58.5,"rank":64},"arena_text":1372.982853047627,"arena_text_rank":196,"arena_text_rating_lower":1368.7295054947192,"arena_text_rating_upper":1377.2362006005346,"arena_text_vote_count":30660,"arena_text_date":"2026-10-15","arena_creative_writing":1327.487846165283,"arena_creative_writing_rank":205,"arena_creative_writing_rating_lower":1317.9034997532249,"arena_creative_writing_rating_upper":1337.0721925773407,"arena_creative_writing_vote_count":3999,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k3","name":"Kimi K3","provider":"ember","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":2.7,"output":13.5,"cache_read":0.27,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","provider":"ember","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.635,"output":2.9699999999999998,"cache_read":0.162,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"kimi-k2.6","name":"Kimi K2.6","provider":"ember","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.855,"output":3.5999999999999996,"cache_read":0.144,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k2.5","name":"Kimi K2.5","provider":"ember","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.35624999999999996,"output":1.9800000000000002,"cache_read":0.22499999999999998,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-27","knowledge_cutoff":"2025-01","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.5,"coding_index":46.8,"agentic_index":null,"design_arena_best":{"category":"website","elo":1248,"win_rate":55.2,"rank":45}}},{"id":"minimax-m3","name":"MiniMax M3","provider":"ember","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.27,"output":1.08,"cache_read":0.054,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-01","knowledge_cutoff":null,"description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax-m2.7","name":"MiniMax M2.7","provider":"ember","quantization":null,"discount":0,"context_length":204800,"pricing":{"input":0.27,"output":1.08,"cache_read":0.054,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-18","knowledge_cutoff":null,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":52.6,"agentic_index":15.3,"design_arena_best":{"category":"website","elo":1241,"win_rate":51.3,"rank":49},"arena_text":1415.0035341569967,"arena_text_rank":140,"arena_text_rating_lower":1411.653118390283,"arena_text_rating_upper":1418.3539499237102,"arena_text_vote_count":84977,"arena_text_date":"2026-10-15","arena_creative_writing":1363.9436635426205,"arena_creative_writing_rank":165,"arena_creative_writing_rating_lower":1357.8156580924347,"arena_creative_writing_rating_upper":1370.071668992806,"arena_creative_writing_vote_count":14495,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax-m2.5","name":"MiniMax M2.5","provider":"ember","quantization":null,"discount":0,"context_length":196608,"pricing":{"input":0.14250000000000002,"output":0.855,"cache_read":0.04,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"modified-mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1222,"win_rate":57.5,"rank":59},"arena_text":1390.6393248159263,"arena_text_rank":176,"arena_text_rating_lower":1386.7507469142622,"arena_text_rating_upper":1394.5279027175907,"arena_text_vote_count":42815,"arena_text_date":"2026-10-15","arena_creative_writing":1356.158261008215,"arena_creative_writing_rank":173,"arena_creative_writing_rating_lower":1348.2833131092946,"arena_creative_writing_rating_upper":1364.0332089071358,"arena_creative_writing_vote_count":6671,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","provider":"ember","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.851,"output":1.703,"cache_read":0.071,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","provider":"ember","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.0645,"output":0.129,"cache_read":0.0128,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3-coder-next","name":"Qwen3 Coder Next","provider":"ember","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.108,"output":0.675,"cache_read":0.06,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-03","knowledge_cutoff":"2025-09","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":36.2,"agentic_index":0.9,"design_arena_best":null}},{"id":"GLM-5.2","name":"GLM-5.2","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.19,"output":4.4,"cache_read":0.18,"cache_write":0},"org":"z-ai","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://pass.wafer.ai/v1","model_id":"GLM-5.2","doc_url":"https://docs.wafer.ai/wafer-pass","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"GLM-5.3","name":"GLM-5.3","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.3,"output":3,"cache_read":0.18,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"Kimi-K3","name":"Kimi-K3","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":2,"output":15,"cache_read":0.25,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen3.8-27B","name":"Qwen3.8-27B","provider":"wafer","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.06,"output":2.3,"cache_read":0.05,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"GLM-5.3-Flash","name":"GLM-5.3-Flash","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.05,"output":0.2,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"DeepSeek-V4-Pro","name":"DeepSeek-V4-Pro","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.28,"output":3.96,"cache_read":0.04,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"DeepSeek-V4.1-Flash","name":"DeepSeek-V4.1-Flash","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.19,"output":0.65,"cache_read":0.01,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"DeepSeek-V4-Flash-0423","name":"DeepSeek-V4-Flash-0423","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.14,"output":0.28,"cache_read":0.03,"cache_write":null},"org":"wafer","open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"DeepSeek-V4.1-Flash-1017","name":"DeepSeek-V4.1-Flash-1017","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.13,"output":0.5,"cache_read":0,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"DeepSeek-V4-Flash-0731-Fast","name":"DeepSeek-V4-Flash-0731-Fast","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.13,"output":0.23,"cache_read":0.03,"cache_write":null},"org":"wafer","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.venice.ai","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"syn:large:text","name":"syn:large:text","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"deepseek","pricing":{"input":0.6,"output":1.2,"cache_read":0.12,"cache_write":null},"zdr":true,"subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"syn:small:text","name":"syn:small:text","provider":"synthetic","quantization":null,"discount":0,"context_length":196608,"org":"z-ai","pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.02,"cache_write":null},"zdr":true,"subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"syn:large:vision","name":"syn:large:vision","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"moonshot","pricing":{"input":3,"output":15,"cache_read":0.6000000000000001,"cache_write":null},"zdr":true,"subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"syn:small:vision","name":"syn:small:vision","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"deepseek","pricing":{"input":0.6,"output":1.2,"cache_read":0.12,"cache_write":null},"zdr":true,"subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"hf:openai/gpt-oss-120b","name":"openai/gpt-oss-120b","provider":"synthetic","quantization":null,"discount":0,"context_length":131072,"org":"openai","pricing":{"input":0.09999999999999999,"output":0.09999999999999999,"cache_read":0.02,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:openai/gpt-oss-120b","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"hf:zai-org/GLM-5.3","name":"zai-org/GLM-5.3","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"z-ai","pricing":{"input":1.4,"output":4.4,"cache_read":0.27999999999999997,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:zai-org/GLM-5.3","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"hf:zai-org/GLM-5.3-Flash","name":"zai-org/GLM-5.3-Flash","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"z-ai","pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:zai-org/GLM-5.3-Flash","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"hf:deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"deepseek","pricing":{"input":0.6,"output":1.2,"cache_read":0.12,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:deepseek-ai/DeepSeek-V4.1-Flash-1017","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"hf:deepseek-ai/DeepSeek-V4.1-Flash","name":"deepseek-ai/DeepSeek-V4.1-Flash","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"deepseek","pricing":{"input":0.6,"output":1.2,"cache_read":0.12,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:deepseek-ai/DeepSeek-V4.1-Flash","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"hf:moonshotai/Kimi-K3","name":"moonshotai/Kimi-K3","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"moonshot","pricing":{"input":3,"output":15,"cache_read":0.6000000000000001,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:moonshotai/Kimi-K3","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"hf:Qwen/Qwen3.8-27B","name":"Qwen/Qwen3.8-27B","provider":"synthetic","quantization":null,"discount":0,"context_length":262144,"org":"qwen","pricing":{"input":0.44999999999999996,"output":2.2,"cache_read":0.09,"cache_write":null},"zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"hf:zai-org/GLM-4.7-Flash","name":"zai-org/GLM-4.7-Flash","provider":"synthetic","quantization":null,"discount":0,"context_length":196608,"org":"z-ai","pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.02,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:zai-org/GLM-4.7-Flash","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-01-19","knowledge_cutoff":"2025-04","description":"Budget GLM lane for fast coding help, routing, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":14.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1202,"win_rate":57.6,"rank":60},"arena_text":1364.5160203965402,"arena_text_rank":201,"arena_text_rating_lower":1358.8016752228536,"arena_text_rating_upper":1370.230365570227,"arena_text_vote_count":12021,"arena_text_date":"2026-10-15","arena_creative_writing":1304.7675155862905,"arena_creative_writing_rank":230,"arena_creative_writing_rating_lower":1291.0131953224686,"arena_creative_writing_rating_upper":1318.5218358501124,"arena_creative_writing_vote_count":1873,"arena_creative_writing_date":"2026-10-15"}},{"id":"hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","name":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","provider":"synthetic","quantization":"nvfp4","discount":0,"context_length":262144,"org":"nvidia","pricing":{"input":0.3,"output":1,"cache_read":0.06,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-03-11","knowledge_cutoff":"2025-06","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.8,"coding_index":37.7,"agentic_index":1.7,"design_arena_best":null,"arena_text":1360.080568965112,"arena_text_rank":206,"arena_text_rating_lower":1352.9580190563502,"arena_text_rating_upper":1367.2031188738738,"arena_text_vote_count":7878,"arena_text_date":"2026-10-15","arena_creative_writing":1303.567788198394,"arena_creative_writing_rank":234,"arena_creative_writing_rating_lower":1285.8236973217145,"arena_creative_writing_rating_upper":1321.3118790750734,"arena_creative_writing_vote_count":1121,"arena_creative_writing_date":"2026-10-15"}},{"id":"DeepSeek-V3.1","name":"DeepSeek-V3.1","org":"deepseek","provider":"sambanova","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":3,"output":4.5,"cache_read":null,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-21","knowledge_cutoff":null,"description":"A large hybrid model that supports both thinking and non-thinking modes via prompt templates.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1417.0286131400032,"arena_text_rank":135,"arena_text_rating_lower":1410.9662146935234,"arena_text_rating_upper":1423.0910115864833,"arena_text_vote_count":14610,"arena_text_date":"2026-10-15","arena_creative_writing":1387.9765537688254,"arena_creative_writing_rank":134,"arena_creative_writing_rating_lower":1374.5186597419859,"arena_creative_writing_rating_upper":1401.4344477956652,"arena_creative_writing_vote_count":1978,"arena_creative_writing_date":"2026-10-15"}},{"id":"DeepSeek-V3.2","name":"DeepSeek-V3.2","org":"deepseek","provider":"sambanova","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":3,"output":4.5,"cache_read":null,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"Meta-Llama-3.3-70B-Instruct","name":"Meta-Llama-3.3-70B-Instruct","org":"meta","provider":"sambanova","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.6,"output":1.2,"cache_read":null,"cache_write":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null,"design_arena_best":null,"arena_text":1318.0654473917496,"arena_text_rank":264,"arena_text_rating_lower":1314.561524832038,"arena_text_rating_upper":1321.569369951461,"arena_text_vote_count":54497,"arena_text_date":"2026-10-15","arena_creative_writing":1285.365717788876,"arena_creative_writing_rank":257,"arena_creative_writing_rating_lower":1278.3092286350516,"arena_creative_writing_rating_upper":1292.4222069427008,"arena_creative_writing_vote_count":8046,"arena_creative_writing_date":"2026-10-15"}},{"id":"MiniMax-M3.1-Flash","name":"MiniMax-M3.1-Flash","org":"minimax","provider":"sambanova","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"gemma-4-31B-it","name":"gemma-4-31B-it","org":"google","provider":"sambanova","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.38,"output":1.15,"cache_read":null,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"gpt-oss-120b","name":"gpt-oss-120b","org":"openai","provider":"sambanova","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.22,"output":0.59,"cache_read":null,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"prism","name":"Prism","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":3.2664,"output":16.332,"cache_read":0.32664,"cache_write":0},"org":"hyper","zdr":true,"subscription":true,"max_completion_tokens":16000,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"prism","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"1970-01-01","knowledge_cutoff":null,"description":"Multimodal model for analyzing text, images, documents, and rich media","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.33,"output":1.31,"cache_read":0.03,"cache_write":0},"org":"deepseek","zdr":true,"subscription":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"deepseek-v4.1-flash-1017","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.33,"output":1.31,"cache_read":0.03,"cache_write":0},"org":"deepseek","zdr":true,"subscription":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"deepseek-v4.1-flash","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.437216,"output":4.311648,"cache_read":0.047907,"cache_write":0},"org":"deepseek","zdr":true,"subscription":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"deepseek-v4-pro-0813","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.44,"output":1.32,"cache_read":0.044,"cache_write":0},"org":"deepseek","zdr":true,"subscription":true,"max_completion_tokens":384000,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"deepseek-v4-flash-0731","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"kimi-k3","name":"Kimi K3","provider":"hyper","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":3.2664,"output":16.332,"cache_read":0.32664,"cache_write":0},"org":"moonshot","zdr":true,"subscription":true,"max_completion_tokens":16000,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"kimi-k3","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","provider":"hyper","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":1.03436,"output":4.3552,"cache_read":0.206872,"cache_write":0},"org":"moonshot","zdr":true,"subscription":true,"max_completion_tokens":16000,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"kimi-k2.7-code","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"kimi-k2-thinking","name":"Kimi K2 Thinking","provider":"hyper","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.6,"output":2.5,"cache_read":0.3,"cache_write":0},"org":"moonshot","zdr":true,"subscription":true,"max_completion_tokens":26214,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"kimi-k2-thinking","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2025-11-06","knowledge_cutoff":"2024-08","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"modified-mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22,"coding_index":21,"agentic_index":null,"design_arena_best":{"category":"website","elo":1111,"win_rate":48.8,"rank":108},"arena_text":1430.0979685766106,"arena_text_rank":116,"arena_text_rating_lower":1427.01038052258,"arena_text_rating_upper":1433.185556630641,"arena_text_vote_count":63368,"arena_text_date":"2026-10-15","arena_creative_writing":1391.2119431696153,"arena_creative_writing_rank":126,"arena_creative_writing_rating_lower":1384.6191198043907,"arena_creative_writing_rating_upper":1397.8047665348402,"arena_creative_writing_vote_count":9534,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3","name":"GLM 5.3","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.52432,"output":4.79072,"cache_read":0.283088,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"max_completion_tokens":128000,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"glm-5.3","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"GLM 5.3 Flash","provider":"hyper","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.16332,"output":0.5444,"cache_read":0.031575,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"glm-5.3-flash","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.2","name":"GLM-5.2","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.52432,"output":4.79072,"cache_read":0.152432,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"max_completion_tokens":32768,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"glm-5.2","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax-m3","name":"MiniMax M3","provider":"hyper","quantization":null,"discount":0,"context_length":512000,"pricing":{"input":0.32664,"output":1.30656,"cache_read":0.064239,"cache_write":0},"org":"minimax","zdr":true,"subscription":true,"max_completion_tokens":512000,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"minimax-m3","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-06-01","knowledge_cutoff":null,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax-m2.7","name":"MiniMax M2.7","provider":"hyper","quantization":null,"discount":0,"context_length":262100,"pricing":{"input":0.484,"output":1.852,"cache_read":0.242,"cache_write":0},"org":"minimax","zdr":true,"subscription":true,"max_completion_tokens":6553,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"minimax-m2.7","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-03-18","knowledge_cutoff":null,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":52.6,"agentic_index":15.3,"design_arena_best":{"category":"website","elo":1241,"win_rate":51.3,"rank":49},"arena_text":1415.0035341569967,"arena_text_rank":140,"arena_text_rating_lower":1411.653118390283,"arena_text_rating_upper":1418.3539499237102,"arena_text_vote_count":84977,"arena_text_date":"2026-10-15","arena_creative_writing":1363.9436635426205,"arena_creative_writing_rank":165,"arena_creative_writing_rating_lower":1357.8156580924347,"arena_creative_writing_rating_upper":1370.071668992806,"arena_creative_writing_vote_count":14495,"arena_creative_writing_date":"2026-10-15"}},{"id":"inkling","name":"Inkling","provider":"hyper","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1.0888,"output":4.40964,"cache_read":0.185096,"cache_write":0},"org":"thinkingmachines","zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"inkling","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-07-15","knowledge_cutoff":null,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.5,"coding_index":52.1,"agentic_index":22.5,"design_arena_best":{"category":"website","elo":1224,"win_rate":44.7,"rank":58},"arena_text":1440.8717396141749,"arena_text_rank":97,"arena_text_rating_lower":1436.5585433735794,"arena_text_rating_upper":1445.1849358547706,"arena_text_vote_count":40648,"arena_text_date":"2026-10-15","arena_creative_writing":1380.9974874241316,"arena_creative_writing_rank":144,"arena_creative_writing_rating_lower":1373.523053280632,"arena_creative_writing_rating_upper":1388.4719215676314,"arena_creative_writing_vote_count":8748,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3.8-max","name":"Qwen3.8-Max","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2,"output":6,"cache_read":0.25,"cache_write":0},"org":"qwen","zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"qwen3.8-max","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-07-19","knowledge_cutoff":null,"description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":45.4,"coding_index":76.2,"agentic_index":56,"design_arena_best":null,"arena_text":1482.3530183862679,"arena_text_rank":24,"arena_text_rating_lower":1477.3762943638942,"arena_text_rating_upper":1487.3297424086413,"arena_text_vote_count":27766,"arena_text_date":"2026-10-15","arena_creative_writing":1468.9997777918718,"arena_creative_writing_rank":19,"arena_creative_writing_rating_lower":1459.9936527553632,"arena_creative_writing_rating_upper":1478.0059028283804,"arena_creative_writing_vote_count":5471,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3.8-flash","name":"Qwen3.8-Flash","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0},"org":"qwen","zdr":true,"subscription":true,"max_completion_tokens":128000,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"qwen3.8-flash","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen3.8-27b","name":"Qwen3.8-27B","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.5,"output":3,"cache_read":0.1,"cache_write":0},"org":"qwen","zdr":true,"subscription":true,"max_completion_tokens":128000,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"qwen3.8-27b","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3.8-2.4t-a95b","name":"Qwen3.8-2.4T-A95B","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2,"output":6,"cache_read":0.25,"cache_write":0},"org":"qwen","zdr":true,"subscription":true,"max_completion_tokens":128000,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"qwen3.8-2.4t-a95b","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-08-12","knowledge_cutoff":null,"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"qwen3.8-max","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.9,"coding_index":71.9,"agentic_index":50.1,"design_arena_best":null}},{"id":"qwen3.7-max","name":"Qwen3.7-Max","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":0},"org":"qwen","zdr":true,"subscription":true,"max_completion_tokens":64000,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"qwen3.7-max","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-05-21","knowledge_cutoff":null,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.5,"coding_index":66,"agentic_index":22.5,"design_arena_best":{"category":"dataviz","elo":1276,"win_rate":53,"rank":24},"arena_text":1474.346453572102,"arena_text_rank":39,"arena_text_rating_lower":1464.6199672413577,"arena_text_rating_upper":1484.0729399028464,"arena_text_vote_count":3934,"arena_text_date":"2026-10-15","arena_creative_writing":1439.2456129096304,"arena_creative_writing_rank":60,"arena_creative_writing_rating_lower":1411.9628845744933,"arena_creative_writing_rating_upper":1466.5283412447675,"arena_creative_writing_vote_count":508,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3.7-plus","name":"Qwen3.7-Plus","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.2,"output":4.8,"cache_read":0.24,"cache_write":0},"org":"qwen","zdr":true,"subscription":true,"max_completion_tokens":64000,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"qwen3.7-plus","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-06-02","knowledge_cutoff":"2025-04","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.2,"coding_index":55.9,"agentic_index":17.5,"design_arena_best":{"category":"dataviz","elo":1279,"win_rate":51.3,"rank":22},"arena_text":1455.682715060256,"arena_text_rank":69,"arena_text_rating_lower":1451.3500504663698,"arena_text_rating_upper":1460.0153796541422,"arena_text_vote_count":42075,"arena_text_date":"2026-10-15","arena_creative_writing":1431.499455939465,"arena_creative_writing_rank":72,"arena_creative_writing_rating_lower":1423.8736889483803,"arena_creative_writing_rating_upper":1439.1252229305496,"arena_creative_writing_vote_count":7841,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3.7-flash","name":"Qwen3.7-Flash","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.2,"output":0.8,"cache_read":0.04,"cache_write":0},"org":"qwen","zdr":true,"subscription":true,"max_completion_tokens":64000,"max_prompt_tokens":991808,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"qwen3.7-flash","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-07-15","knowledge_cutoff":null,"description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"gpt-oss-120b","name":"gpt-oss-120b","provider":"hyper","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.178,"output":0.68,"cache_read":0.089,"cache_write":0},"org":"openai","zdr":true,"subscription":true,"max_completion_tokens":13107,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"gpt-oss-120b","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","provider":"hyper","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.098,"output":0.334,"cache_read":0.049,"cache_write":0},"org":"google","zdr":true,"subscription":true,"max_completion_tokens":25600,"modelsdev":{"base_url":"https://hyper.charm.land/v1","model_id":"gemma-4-26b-a4b-it","doc_url":"https://hyper.charm.land","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","provider":"sference","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":3,"output":15,"cache_read":0.45,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"zai-org/GLM-5.2","name":"GLM 5.2","provider":"sference","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1.2,"output":4.2,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM 5.3 Flash","provider":"sference","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.2,"output":0.6,"cache_read":0.07,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"zai-org/GLM-5.3","name":"GLM 5.3","provider":"sference","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1.2,"output":4.2,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","provider":"sference","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.28,"output":0.56,"cache_read":0.07,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash (0731)","provider":"sference","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.28,"output":0.56,"cache_read":0.07,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek V4.1 Flash (1017)","provider":"sference","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.5,"output":1.5,"cache_read":0.05,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","provider":"sference","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.5,"output":1.5,"cache_read":0.05,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen-3.8-27b","name":"Qwen 3.8 27B","provider":"neuralwatt","quantization":null,"discount":0,"context_length":262128,"pricing":{"input":0.45,"output":3.2,"cache_read":0.25,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"qwen-3.8-27b","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen-3.8-27b:flex","name":"Qwen 3.8 27B (flex)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":262128,"pricing":{"input":0.2925,"output":2.08,"cache_read":0.1625,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"qwen-3.8-27b","doc_url":"https://portal.neuralwatt.com/docs","confidence":"medium","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.87,"output":1.74,"cache_read":0.036,"cache_write":null},"org":"xiaomi","zdr":true,"max_completion_tokens":393216,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"mimo-v2.6-pro","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":null,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1335,"win_rate":58.4,"rank":7},"arena_text":1479.194755229377,"arena_text_rank":27,"arena_text_rating_lower":1469.827446672319,"arena_text_rating_upper":1488.5620637864351,"arena_text_vote_count":4075,"arena_text_date":"2026-10-15","arena_creative_writing":1444.679173566022,"arena_creative_writing_rank":52,"arena_creative_writing_rating_lower":1423.5979241643079,"arena_creative_writing_rating_upper":1465.760422967736,"arena_creative_writing_vote_count":793,"arena_creative_writing_date":"2026-10-15"}},{"id":"mimo-v2.6-pro:flex","name":"MiMo-V2.6-Pro (flex)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.5655,"output":1.131,"cache_read":0.0234,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":393216,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"mimo-v2.6-pro","doc_url":"https://portal.neuralwatt.com/docs","confidence":"medium","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":null,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1335,"win_rate":58.4,"rank":7},"arena_text":1479.194755229377,"arena_text_rank":27,"arena_text_rating_lower":1469.827446672319,"arena_text_rating_upper":1488.5620637864351,"arena_text_vote_count":4075,"arena_text_date":"2026-10-15","arena_creative_writing":1444.679173566022,"arena_creative_writing_rank":52,"arena_creative_writing_rating_lower":1423.5979241643079,"arena_creative_writing_rating_upper":1465.760422967736,"arena_creative_writing_vote_count":793,"arena_creative_writing_date":"2026-10-15"}},{"id":"nw-large","name":"Neuralwatt Large","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"neuralwatt","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"nw-large:flex","name":"Neuralwatt Large (flex)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":1.95,"output":9.75,"cache_read":0.195,"cache_write":null},"org":"neuralwatt","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"nw-flash","name":"Neuralwatt Flash","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"neuralwatt","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"nw-flash:flex","name":"Neuralwatt Flash (flex)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.0975,"output":0.39,"cache_read":0.00975,"cache_write":null},"org":"neuralwatt","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"glm-5.3","name":"GLM 5.3","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":1.45,"output":4.5,"cache_read":0.145,"cache_write":null},"org":"z-ai","zdr":true,"max_completion_tokens":1048560,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"glm-5.3","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3:flex","name":"GLM 5.3 (flex)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.9425,"output":2.925,"cache_read":0.09425,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":1048560,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"glm-5.3","doc_url":"https://portal.neuralwatt.com/docs","confidence":"medium","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"max_completion_tokens":1048560,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"glm-5.3-flash","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash:flex","name":"GLM-5.3 Flash (flex)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.0975,"output":0.325,"cache_read":0.0195,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":1048560,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"glm-5.3-flash","doc_url":"https://portal.neuralwatt.com/docs","confidence":"medium","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"nw-small","name":"Neuralwatt Small","provider":"neuralwatt","quantization":null,"discount":0,"context_length":262128,"pricing":{"input":0.45,"output":3.2,"cache_read":0.25,"cache_write":null},"org":"neuralwatt","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"nw-small:flex","name":"Neuralwatt Small (flex)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":262128,"pricing":{"input":0.2925,"output":2.08,"cache_read":0.1625,"cache_write":null},"org":"neuralwatt","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen3.6-35b","name":"Qwen3.6 35B","provider":"neuralwatt","quantization":null,"discount":0,"context_length":262128,"pricing":{"input":0.29,"output":1.15,"cache_read":0.029,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":131056,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"qwen3.6-35b","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"energy":{"source":"https://portal.neuralwatt.com/energy-pricing","rate_usd_per_kwh":10,"measured_window":"7d","workload_dependent":true,"updated_ago":"14m ago","bands":{"0–256":{"wh":0.00622,"share":0.9},"256–1k":{"wh":0.03696,"share":52.2},"1k–4k":{"wh":0.08923,"share":2.3},"4k–16k":{"wh":0.041979999999999996,"share":24},"16k–64k":{"wh":0.03003,"share":16.7},"64k–256k":{"wh":0.16771,"share":3.9},"256k–1M":{"wh":null,"share":null}},"wh_per_mtok":3.252067533982505,"wh_per_mtok_overridden":false,"measured_cached_input_share":0.7333300619223623,"measured_output_share":0.03301390980081772,"cached_energy_fraction":0.15,"estimator_fetched_at":"2026-10-29T20:44:18.463Z","estimator_source":"fresh"}},{"id":"qwen3.6-35b-fast","name":"Qwen3.6 35B Fast","provider":"neuralwatt","quantization":null,"discount":0,"context_length":262128,"pricing":{"input":0.29,"output":1.15,"cache_read":0.029,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":131056,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"qwen3.6-35b-fast","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"energy":{"source":"https://portal.neuralwatt.com/energy-pricing","rate_usd_per_kwh":10,"measured_window":"7d","workload_dependent":true,"updated_ago":"14m ago","bands":{"0–256":{"wh":0.00543,"share":1.6},"256–1k":{"wh":0.009380000000000001,"share":30.4},"1k–4k":{"wh":0.01061,"share":41.7},"4k–16k":{"wh":0.033299999999999996,"share":14.5},"16k–64k":{"wh":0.04474,"share":9.1},"64k–256k":{"wh":0.07309,"share":2.7},"256k–1M":{"wh":null,"share":null}},"wh_per_mtok":2.3244619436133616,"wh_per_mtok_overridden":false,"measured_cached_input_share":0.7406981226115663,"measured_output_share":0.021274834803448835,"cached_energy_fraction":0.15,"estimator_fetched_at":"2026-10-29T20:44:18.463Z","estimator_source":"fresh"}},{"id":"qwen3.6-35b:flex","name":"Qwen3.6 35B (flex)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":262128,"pricing":{"input":0.1885,"output":0.7475,"cache_read":0.01885,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":131056,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"qwen3.6-35b","doc_url":"https://portal.neuralwatt.com/docs","confidence":"medium","source":"models.dev","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":393216,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"deepseek-v4.1-flash","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash:flex","name":"DeepSeek V4.1 Flash (flex)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.0975,"output":0.39,"cache_read":0.00975,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":393216,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"deepseek-v4.1-flash","doc_url":"https://portal.neuralwatt.com/docs","confidence":"medium","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash-speed","name":"DeepSeek V4.1 Flash (Speed)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"neuralwatt","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.14,"output":0.28,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":393216,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"deepseek-v4-flash","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"},"energy":{"source":"https://portal.neuralwatt.com/energy-pricing","rate_usd_per_kwh":10,"measured_window":"7d","workload_dependent":true,"updated_ago":"14m ago","bands":{"0–256":{"wh":0.00231,"share":1.9},"256–1k":{"wh":0.00871,"share":3.7},"1k–4k":{"wh":0.03485,"share":13.5},"4k–16k":{"wh":0.09051999999999999,"share":14.6},"16k–64k":{"wh":0.25849,"share":55.5},"64k–256k":{"wh":0.42599000000000004,"share":9.2},"256k–1M":{"wh":0.67603,"share":1.5}},"wh_per_mtok":13.016170357296467,"wh_per_mtok_overridden":false,"measured_cached_input_share":0.8816500584257291,"measured_output_share":0.03244707615444788,"cached_energy_fraction":0.15,"estimator_fetched_at":"2026-10-29T20:44:18.463Z","estimator_source":"fresh"}},{"id":"deepseek-v4-flash:flex","name":"DeepSeek V4 Flash (flex)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.091,"output":0.182,"cache_read":0.0182,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":393216,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"deepseek-v4-flash","doc_url":"https://portal.neuralwatt.com/docs","confidence":"medium","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-flash-speed","name":"DeepSeek V4 Flash (Speed)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":0.14,"output":0.28,"cache_read":0.028,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":393216,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"deepseek-v4-flash-speed","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"gemma-4-31b","name":"Gemma 4 31B","provider":"neuralwatt","quantization":null,"discount":0,"context_length":262128,"pricing":{"input":0.144,"output":0.42,"cache_read":0.0144,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":16384,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"gemma-4-31b","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1452.1630800897058,"arena_text_rank":76,"arena_text_rating_lower":1444.7266838974383,"arena_text_rating_upper":1459.5994762819735,"arena_text_vote_count":6147,"arena_text_date":"2026-10-15","arena_creative_writing":1418.8100084472562,"arena_creative_writing_rank":86,"arena_creative_writing_rating_lower":1399.993166915414,"arena_creative_writing_rating_upper":1437.6268499790986,"arena_creative_writing_vote_count":974,"arena_creative_writing_date":"2026-10-15"},"energy":{"source":"https://portal.neuralwatt.com/energy-pricing","rate_usd_per_kwh":10,"measured_window":"7d","workload_dependent":true,"updated_ago":"14m ago","bands":{"0–256":{"wh":0.00505,"share":15},"256–1k":{"wh":0.01868,"share":6.7},"1k–4k":{"wh":0.0603,"share":19.5},"4k–16k":{"wh":0.07947,"share":53.4},"16k–64k":{"wh":0.23191,"share":5.1},"64k–256k":{"wh":0.55836,"share":0.3},"256k–1M":{"wh":null,"share":null}},"wh_per_mtok":9.343478768004697,"wh_per_mtok_overridden":false,"measured_cached_input_share":0.6154233980375899,"measured_output_share":0.04276553740267198,"cached_energy_fraction":0.15,"estimator_fetched_at":"2026-10-29T20:44:18.463Z","estimator_source":"fresh"}},{"id":"kimi-k3","name":"Kimi K3","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"max_completion_tokens":1048560,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"kimi-k3","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"},"energy":{"source":"https://portal.neuralwatt.com/energy-pricing","rate_usd_per_kwh":10,"measured_window":"7d","workload_dependent":true,"updated_ago":"14m ago","bands":{"0–256":{"wh":0.045079999999999995,"share":17.7},"256–1k":{"wh":0.36868,"share":1.3},"1k–4k":{"wh":0.7363200000000001,"share":2},"4k–16k":{"wh":1.27,"share":5.7},"16k–64k":{"wh":1.51,"share":20.1},"64k–256k":{"wh":2.42,"share":38.6},"256k–1M":{"wh":2.79,"share":14.7}},"wh_per_mtok":13.98094263267861,"wh_per_mtok_overridden":false,"measured_cached_input_share":0.9661913918148656,"measured_output_share":0.004911975653446539,"cached_energy_fraction":0.15,"estimator_fetched_at":"2026-10-29T20:44:18.463Z","estimator_source":"fresh"}},{"id":"kimi-k3-fast","name":"Kimi K3 Fast","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":1048560,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"kimi-k3-fast","doc_url":"https://portal.neuralwatt.com/docs","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Kimi K3 with thinking disabled for low-latency tool calling, vision, and JSON work","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"},"energy":{"source":"https://portal.neuralwatt.com/energy-pricing","rate_usd_per_kwh":10,"measured_window":"7d","workload_dependent":true,"updated_ago":"14m ago","bands":{"0–256":{"wh":0.14128,"share":1.6},"256–1k":{"wh":0.11621,"share":10.5},"1k–4k":{"wh":0.68403,"share":5.8},"4k–16k":{"wh":0.26893,"share":44.8},"16k–64k":{"wh":0.83429,"share":28.7},"64k–256k":{"wh":1.21,"share":8.6},"256k–1M":{"wh":null,"share":null}},"wh_per_mtok":24.147997955203024,"wh_per_mtok_overridden":false,"measured_cached_input_share":0.8922324006302943,"measured_output_share":0.012486002573406778,"cached_energy_fraction":0.15,"estimator_fetched_at":"2026-10-29T20:44:18.463Z","estimator_source":"fresh"}},{"id":"kimi-k3:flex","name":"Kimi K3 (flex)","provider":"neuralwatt","quantization":null,"discount":0,"context_length":1048560,"pricing":{"input":1.95,"output":9.75,"cache_read":0.195,"cache_write":null},"org":"neuralwatt","zdr":true,"max_completion_tokens":1048560,"modelsdev":{"base_url":"https://api.neuralwatt.com/v1","model_id":"kimi-k3","doc_url":"https://portal.neuralwatt.com/docs","confidence":"medium","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-oss-120b","name":"gpt-oss-120b","org":"openai","provider":"aster","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-oss-120b-fast","name":"gpt-oss-120b-fast","org":"openai","provider":"aster","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"zdr":true,"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.2","name":"glm-5.2","org":"z-ai","provider":"aster","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1,"output":4,"cache_read":0.2,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k3","name":"kimi-k3","org":"moonshot","provider":"aster","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":2.5,"output":12.5,"cache_read":0.25,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"zai-org/glm-5.2:batch","name":"zai-org/glm-5.2-batch","org":"z-ai","provider":"aster","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.75,"output":2.5,"cache_read":null,"cache_write":null},"zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","org":"deepseek","provider":"arilo","quantization":"mxfp4","max_completion_tokens":60000,"discount":0,"context_length":1000000,"pricing":{"input":0.28,"output":0.6,"cache_read":0.01,"cache_write":null},"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","provider":"avian","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":393216,"pricing":{"input":0.1275,"output":0.51,"cache_read":0.00255,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","provider":"avian","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":393216,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","provider":"avian","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":393216,"pricing":{"input":1.305,"output":2.61,"cache_read":0.10875,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","provider":"avian","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":393216,"pricing":{"input":0.561,"output":1.683,"cache_read":0.0187,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2 (Legacy)","provider":"avian","quantization":null,"discount":0,"context_length":163840,"max_completion_tokens":65536,"pricing":{"input":0.23,"output":0.33,"cache_read":0.012,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax M3","provider":"avian","quantization":null,"discount":0,"context_length":524288,"max_completion_tokens":512000,"pricing":{"input":0.255,"output":1.02,"cache_read":0.051,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-01","knowledge_cutoff":null,"description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5","provider":"avian","quantization":null,"discount":0,"context_length":196608,"max_completion_tokens":131072,"pricing":{"input":0.27,"output":1.08,"cache_read":0.15,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"modified-mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1222,"win_rate":57.5,"rank":59},"arena_text":1390.6393248159263,"arena_text_rank":176,"arena_text_rating_lower":1386.7507469142622,"arena_text_rating_upper":1394.5279027175907,"arena_text_vote_count":42815,"arena_text_date":"2026-10-15","arena_creative_writing":1356.158261008215,"arena_creative_writing_rank":173,"arena_creative_writing_rating_lower":1348.2833131092946,"arena_creative_writing_rating_upper":1364.0332089071358,"arena_creative_writing_vote_count":6671,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"GLM-5.3","provider":"avian","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":1.19,"output":3.74,"cache_read":0.221,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3 Flash","provider":"avian","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":0.1275,"output":0.425,"cache_read":0.0255,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.7","name":"GLM-4.7","provider":"avian","quantization":null,"discount":0,"context_length":202752,"max_completion_tokens":131072,"pricing":{"input":0.388,"output":1.806,"cache_read":0.097,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.2,"coding_index":45.3,"agentic_index":null,"design_arena_best":{"category":"website","elo":1224,"win_rate":55.3,"rank":57},"arena_text":1441.3266291777354,"arena_text_rank":95,"arena_text_rating_lower":1435.2694154856003,"arena_text_rating_upper":1447.3838428698703,"arena_text_vote_count":12253,"arena_text_date":"2026-10-15","arena_creative_writing":1404.7365646711344,"arena_creative_writing_rank":102,"arena_creative_writing_rating_lower":1391.4905429408939,"arena_creative_writing_rating_upper":1417.9825864013746,"arena_creative_writing_vote_count":1960,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5","name":"GLM-5","provider":"avian","quantization":null,"discount":0,"context_length":204800,"max_completion_tokens":131072,"pricing":{"input":0.516,"output":2.322,"cache_read":0.129,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"GLM-5.1","provider":"avian","quantization":null,"discount":0,"context_length":202752,"max_completion_tokens":202752,"pricing":{"input":0.743,"output":2.971,"cache_read":0.186,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"GLM-5.2","provider":"avian","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":0.495,"output":1.733,"cache_read":0.124,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","provider":"avian","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":943718,"pricing":{"input":2.55,"output":12.75,"cache_read":0.255,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","provider":"avian","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":262144,"pricing":{"input":0.45,"output":2.2,"cache_read":0.225,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-27","knowledge_cutoff":"2025-01","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.5,"coding_index":46.8,"agentic_index":null,"design_arena_best":{"category":"website","elo":1248,"win_rate":55.2,"rank":45}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","provider":"avian","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":262144,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-flash","name":"MiMo-V2.6 Flash","provider":"avian","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-pro","name":"MiMo-V2.6 Pro","provider":"avian","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":0.36975,"output":0.7395,"cache_read":0.00306,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1335,"win_rate":58.4,"rank":7},"arena_text":1479.194755229377,"arena_text_rank":27,"arena_text_rating_lower":1469.827446672319,"arena_text_rating_upper":1488.5620637864351,"arena_text_vote_count":4075,"arena_text_date":"2026-10-15","arena_creative_writing":1444.679173566022,"arena_creative_writing_rank":52,"arena_creative_writing_rating_lower":1423.5979241643079,"arena_creative_writing_rating_upper":1465.760422967736,"arena_creative_writing_vote_count":793,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo-V2.5 Pro","provider":"avian","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":0.36975,"output":0.7395,"cache_read":0.00306,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26,"coding_index":60.2,"agentic_index":21.3,"design_arena_best":{"category":"codecategories","elo":1266,"win_rate":51.7,"rank":35},"arena_text":1467.2561325712447,"arena_text_rank":49,"arena_text_rating_lower":1463.7152451466172,"arena_text_rating_upper":1470.7970199958725,"arena_text_vote_count":75721,"arena_text_date":"2026-10-15","arena_creative_writing":1433.903257618414,"arena_creative_writing_rank":67,"arena_creative_writing_rating_lower":1427.7056499079981,"arena_creative_writing_rating_upper":1440.10086532883,"arena_creative_writing_vote_count":14122,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3.6-35b-a3b:batch","name":"Qwen3.6 35B (batch)","org":"qwen","provider":"batchrate","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":0.05,"output":0.4,"cache_read":null,"cache_write":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"qwen3.8-27b:batch","name":"Qwen3.8 27B (batch)","org":"qwen","provider":"batchrate","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":0.19,"output":1.12,"cache_read":null,"cache_write":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-oss-120b:batch","name":"gpt-oss 120B (batch)","org":"openai","provider":"batchrate","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":0.06,"output":0.225,"cache_read":null,"cache_write":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-oss-20b:batch","name":"gpt-oss 20B (batch)","org":"openai","provider":"batchrate","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":0.015,"output":0.0525,"cache_read":null,"cache_write":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"gemma-4-26b-a4b:batch","name":"Gemma 4 26B A4B (batch)","org":"batchrate","provider":"batchrate","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":0.0375,"output":0.1275,"cache_read":null,"cache_write":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1437.519731525164,"arena_text_rank":101,"arena_text_rating_lower":1430.082988387981,"arena_text_rating_upper":1444.956474662347,"arena_text_vote_count":6094,"arena_text_date":"2026-10-15","arena_creative_writing":1399.2858260617113,"arena_creative_writing_rank":112,"arena_creative_writing_rating_lower":1380.9697731856947,"arena_creative_writing_rating_upper":1417.601878937728,"arena_creative_writing_vote_count":1001,"arena_creative_writing_date":"2026-10-15"}},{"id":"olmocr-2-7b-1025:batch","name":"olmOCR 2 7B (batch)","org":"batchrate","provider":"batchrate","quantization":null,"discount":0,"context_length":16384,"pricing":{"input":0.075,"output":0.075,"cache_read":null,"cache_write":null},"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen3-vl-30b-a3b:batch","name":"Qwen3 VL 30B A3B (batch)","org":"qwen","provider":"batchrate","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":0.06,"output":0.225,"cache_read":null,"cache_write":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"batchrate-decide:batch","name":"Decisions (batch)","org":"batchrate","provider":"batchrate","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":0.02,"output":null,"cache_read":null,"cache_write":null},"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v4.1-flash-fast","name":"DeepSeek V4.1 Flash Fast","org":"deepseek","provider":"coralbricks","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":393216,"pricing":{"input":0.45,"output":1.8,"cache_read":0.009,"cache_write":0.45,"cache_write_addon":0,"input_billing":"cache_write"},"modelsdev":{"base_url":"https://inference.coralbricks.ai/v1","model_id":"deepseek-v4.1-flash-fast","doc_url":"https://www.coralbricks.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash Standard","org":"deepseek","provider":"coralbricks","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":393216,"pricing":{"input":0.19,"output":0.6,"cache_read":0.008,"cache_write":0.19,"cache_write_addon":0,"input_billing":"cache_write"},"modelsdev":{"base_url":"https://inference.coralbricks.ai/v1","model_id":"deepseek-v4.1-flash-fast","doc_url":"https://www.coralbricks.ai/docs","confidence":"medium","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"claude-fable-5.1","name":"claude-fable-5.1","org":"anthropic","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":10,"output":50,"cache_read":0.15,"cache_write":7.5},"zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.7,"coding_index":80.7,"agentic_index":57.2,"design_arena_best":{"category":"spreadsheet","elo":1416,"win_rate":70.4,"rank":1},"arena_text":1502.2862278899863,"arena_text_rank":6,"arena_text_rating_lower":1496.239481927182,"arena_text_rating_upper":1508.3329738527907,"arena_text_vote_count":14590,"arena_text_date":"2026-10-15","arena_creative_writing":1484.729535554378,"arena_creative_writing_rank":9,"arena_creative_writing_rating_lower":1473.299210694477,"arena_creative_writing_rating_upper":1496.1598604142787,"arena_creative_writing_vote_count":3284,"arena_creative_writing_date":"2026-10-15"}},{"id":"claude-haiku-5-5","name":"claude-haiku-5-5","org":"anthropic","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":0.1,"output":0.5,"cache_read":0.006,"cache_write":0.075},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-07","knowledge_cutoff":"2026-06","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"claude-opus-5-5","name":"claude-opus-5-5","org":"anthropic","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":3,"output":16,"cache_read":0.12,"cache_write":3},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":"2026-06","description":"Claude model for long-running agentic coding and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"claude-sonnet-5-5","name":"claude-sonnet-5-5","org":"anthropic","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":2,"output":10,"cache_read":0.12,"cache_write":1.5},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-28","knowledge_cutoff":"2026-06","description":"Fast Claude model for everyday coding, agents, and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v3.2","name":"deepseek-v3.2","org":"deepseek","provider":"singularity","quantization":null,"discount":0,"context_length":128000,"max_completion_tokens":128000,"pricing":{"input":0.186,"output":0.28,"cache_read":null,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-flash","name":"deepseek-v4-flash","org":"deepseek","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":384000,"pricing":{"input":0.081,"output":0.162,"cache_read":0.007,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-flash-0731","name":"deepseek-v4-flash-0731","org":"deepseek","provider":"singularity","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":384000,"pricing":{"input":0.2,"output":0.5,"cache_read":0.007,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek-v4-pro","name":"deepseek-v4-pro","org":"deepseek","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":384000,"pricing":{"input":0.392,"output":0.783,"cache_read":0.128,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash","name":"deepseek-v4.1-flash","org":"deepseek","provider":"singularity","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":384000,"pricing":{"input":0.13,"output":0.5,"cache_read":0.003,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash-1017","name":"deepseek-v4.1-flash-1017","org":"deepseek","provider":"singularity","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":393216,"pricing":{"input":0.09,"output":0.36,"cache_read":0.0018,"cache_write":0.09},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"glm-5.3","name":"glm-5.3","org":"z-ai","provider":"singularity","quantization":null,"discount":0,"context_length":1048573,"max_completion_tokens":131072,"pricing":{"input":1.17,"output":3.96,"cache_read":0.245,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-5.6-luna","name":"gpt-5.6-luna","org":"openai","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":0.18,"output":1.1,"cache_read":0.02,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":37.3,"coding_index":71.4,"agentic_index":42.1,"design_arena_best":null,"arena_text":1452.5662458726235,"arena_text_rank":75,"arena_text_rating_lower":1448.2646893469653,"arena_text_rating_upper":1456.8678023982818,"arena_text_vote_count":41109,"arena_text_date":"2026-10-15","arena_creative_writing":1409.8692518077291,"arena_creative_writing_rank":92,"arena_creative_writing_rating_lower":1402.2779905913478,"arena_creative_writing_rating_upper":1417.4605130241107,"arena_creative_writing_vote_count":8603,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-5.6-sol","name":"gpt-5.6-sol","org":"openai","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":2.4,"output":14,"cache_read":0.2,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":78.3,"agentic_index":47.4,"design_arena_best":null,"arena_text":1484.7394950911005,"arena_text_rank":21,"arena_text_rating_lower":1480.4011455154182,"arena_text_rating_upper":1489.077844666783,"arena_text_vote_count":40442,"arena_text_date":"2026-10-15","arena_creative_writing":1468.63029595999,"arena_creative_writing_rank":20,"arena_creative_writing_rating_lower":1460.9860742346168,"arena_creative_writing_rating_upper":1476.2745176853632,"arena_creative_writing_vote_count":8408,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-5.6-terra","name":"gpt-5.6-terra","org":"openai","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":1.8,"output":10,"cache_read":0.2,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":42.1,"coding_index":76.7,"agentic_index":43.2,"design_arena_best":null,"arena_text":1466.429395420974,"arena_text_rank":51,"arena_text_rating_lower":1462.172843173263,"arena_text_rating_upper":1470.685947668685,"arena_text_vote_count":43271,"arena_text_date":"2026-10-15","arena_creative_writing":1428.587050633098,"arena_creative_writing_rank":75,"arena_creative_writing_rating_lower":1421.1965094532784,"arena_creative_writing_rating_upper":1435.9775918129178,"arena_creative_writing_vote_count":9176,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-6-astra","name":"gpt-6-astra","org":"openai","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":8,"output":30,"cache_read":1,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-04","knowledge_cutoff":"2026-04-30","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":56.9,"coding_index":76.9,"agentic_index":51,"design_arena_best":null,"arena_text":1477.319231586918,"arena_text_rank":30,"arena_text_rating_lower":1471.0194563904267,"arena_text_rating_upper":1483.6190067834093,"arena_text_vote_count":12163,"arena_text_date":"2026-10-15","arena_creative_writing":1449.932706761758,"arena_creative_writing_rank":38,"arena_creative_writing_rating_lower":1437.6886399434397,"arena_creative_writing_rating_upper":1462.1767735800763,"arena_creative_writing_vote_count":2718,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-6-luna","name":"gpt-6-luna","org":"openai","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":"2026-05-18","description":"OpenAI's most efficient model for focused, high-volume tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.8,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1442.8129943072395,"arena_text_rank":91,"arena_text_rating_lower":1438.1883147148455,"arena_text_rating_upper":1447.4376738996334,"arena_text_vote_count":49617,"arena_text_date":"2026-10-15","arena_creative_writing":1410.0344781879853,"arena_creative_writing_rank":91,"arena_creative_writing_rating_lower":1402.9014608939249,"arena_creative_writing_rating_upper":1417.1674954820458,"arena_creative_writing_vote_count":11078,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-6-sol","name":"gpt-6-sol","org":"openai","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":1.8,"output":8,"cache_read":0.2,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":"2026-04-20","description":"OpenAI model for complex coding and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":47.6,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1459.0243436054134,"arena_text_rank":61,"arena_text_rating_lower":1452.6775146046048,"arena_text_rating_upper":1465.3711726062222,"arena_text_vote_count":12466,"arena_text_date":"2026-10-15","arena_creative_writing":1437.8631741285064,"arena_creative_writing_rank":61,"arena_creative_writing_rating_lower":1425.2067651679,"arena_creative_writing_rating_upper":1450.519583089113,"arena_creative_writing_vote_count":2587,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-6.1-sol","name":"gpt-6.1-sol","org":"openai","provider":"singularity","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":2,"output":10,"cache_read":0.1,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-29","knowledge_cutoff":"2026-04-30","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1437,"win_rate":59.7,"rank":4},"arena_text":1483.8469422064072,"arena_text_rank":22,"arena_text_rating_lower":1475.7115409166886,"arena_text_rating_upper":1491.982343496126,"arena_text_vote_count":6320,"arena_text_date":"2026-10-15","arena_creative_writing":1458.4355581436328,"arena_creative_writing_rank":30,"arena_creative_writing_rating_lower":1441.4558548127359,"arena_creative_writing_rating_upper":1475.4152614745296,"arena_creative_writing_vote_count":1419,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k2.6","name":"kimi-k2.6","org":"moonshot","provider":"singularity","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":262144,"pricing":{"input":0.581,"output":2.448,"cache_read":0.128,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k2.7-code","name":"kimi-k2.7-code","org":"moonshot","provider":"singularity","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":262144,"pricing":{"input":0.639,"output":3.15,"cache_read":0.152,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"kimi-k3","name":"kimi-k3","org":"moonshot","provider":"singularity","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":262144,"pricing":{"input":2.5,"output":14,"cache_read":0.3,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","org":"deepseek","provider":"runinfra","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":1048576,"pricing":{"input":0.14,"output":0.58,"cache_read":0.03,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.venice.ai","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-1-flash-1017","name":"DeepSeek V4.1 Flash 1017","org":"deepseek","provider":"runinfra","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":1048576,"pricing":{"input":0.15,"output":0.6,"cache_read":0.01,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.mistral.ai/getting-started/models/","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"glm-5-3","name":"GLM 5.3","org":"z-ai","provider":"runinfra","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":1048576,"pricing":{"input":1.3,"output":4.2,"cache_read":0.13,"cache_write":null},"zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"glm-5-3-flash","name":"GLM 5.3 Flash","org":"z-ai","provider":"runinfra","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":1048576,"pricing":{"input":0.05,"output":0.22,"cache_read":0.01,"cache_write":null},"zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"nemotron-3-5-lightning-30b","name":"Nemotron 3.5 Lightning 30B","org":"nvidia","provider":"runinfra","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":262144,"pricing":{"input":0.05,"output":0.15,"cache_read":0.01,"cache_write":null},"zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"ornith-1-5-122b","name":"Ornith 1.5 122B","org":"ornith","provider":"runinfra","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":262144,"pricing":{"input":0.26,"output":2.08,"cache_read":0.07,"cache_write":null},"zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"ornith-1-5-35b","name":"Ornith 1.5 35B","org":"ornith","provider":"runinfra","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":262144,"pricing":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":null},"zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen3-8-27b","name":"Qwen3.8 27B","org":"qwen","provider":"runinfra","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":262144,"pricing":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":null},"zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"gpt-oss-120b","name":"GPT OSS 120B","org":"openai","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":131072,"max_completion_tokens":32000,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.02,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-oss-120b","name":"GPT OSS 120B","org":"openai","provider":"scx-ai","provider_display":"SCX.ai","quantization":null,"discount":0,"context_length":131072,"max_completion_tokens":32768,"pricing":{"input":0.16999999999999998,"output":0.55,"cache_read":null,"cache_write":null},"modelsdev":{"base_url":"https://api.scx.ai/v1","model_id":"gpt-oss-120b","doc_url":"https://platform.scx.ai/docs","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-oss-120b","name":"GPT OSS 120B","org":"openai","provider":"runware","provider_display":"Runware","quantization":null,"discount":0,"context_length":131072,"max_completion_tokens":32768,"pricing":{"input":0.032,"output":0.14,"cache_read":0.032,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-oss-20b","name":"GPT OSS 20B","org":"openai","provider":"consensusprotocol","provider_display":"Consensus Protocol","quantization":null,"discount":0,"context_length":131072,"max_completion_tokens":32766,"pricing":{"input":0.04,"output":0.19,"cache_read":0.01,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Lower latency Mixture-of-Experts model trained on OpenAI's Harmony response format with reasoning capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","org":"openai","provider":"aws-mantle","provider_display":"Aws Mantle","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":128000,"pricing":{"input":4.4,"output":22,"cache_read":0.44,"cache_write":5.5},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":78.3,"agentic_index":47.4,"design_arena_best":null,"arena_text":1484.7394950911005,"arena_text_rank":21,"arena_text_rating_lower":1480.4011455154182,"arena_text_rating_upper":1489.077844666783,"arena_text_vote_count":40442,"arena_text_date":"2026-10-15","arena_creative_writing":1468.63029595999,"arena_creative_writing_rank":20,"arena_creative_writing_rating_lower":1460.9860742346168,"arena_creative_writing_rating_upper":1476.2745176853632,"arena_creative_writing_vote_count":8408,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","org":"openai","provider":"aws-mantle","provider_display":"Aws Mantle","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":128000,"pricing":{"input":2.2,"output":13.200000000000001,"cache_read":0.22,"cache_write":2.75},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":42.1,"coding_index":76.7,"agentic_index":43.2,"design_arena_best":null,"arena_text":1466.429395420974,"arena_text_rank":51,"arena_text_rating_lower":1462.172843173263,"arena_text_rating_upper":1470.685947668685,"arena_text_vote_count":43271,"arena_text_date":"2026-10-15","arena_creative_writing":1428.587050633098,"arena_creative_writing_rank":75,"arena_creative_writing_rating_lower":1421.1965094532784,"arena_creative_writing_rating_upper":1435.9775918129178,"arena_creative_writing_vote_count":9176,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","org":"openai","provider":"aws-mantle","provider_display":"Aws Mantle","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":128000,"pricing":{"input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":37.3,"coding_index":71.4,"agentic_index":42.1,"design_arena_best":null,"arena_text":1452.5662458726235,"arena_text_rank":75,"arena_text_rating_lower":1448.2646893469653,"arena_text_rating_upper":1456.8678023982818,"arena_text_vote_count":41109,"arena_text_date":"2026-10-15","arena_creative_writing":1409.8692518077291,"arena_creative_writing_rank":92,"arena_creative_writing_rating_lower":1402.2779905913478,"arena_creative_writing_rating_upper":1417.4605130241107,"arena_creative_writing_vote_count":8603,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-6-astra","name":"GPT-6 Astra","org":"openai","provider":"aws-mantle","provider_display":"Aws Mantle","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":128000,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-04","knowledge_cutoff":"2026-04-30","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":56.9,"coding_index":76.9,"agentic_index":51,"design_arena_best":null,"arena_text":1477.319231586918,"arena_text_rank":30,"arena_text_rating_lower":1471.0194563904267,"arena_text_rating_upper":1483.6190067834093,"arena_text_vote_count":12163,"arena_text_date":"2026-10-15","arena_creative_writing":1449.932706761758,"arena_creative_writing_rank":38,"arena_creative_writing_rating_lower":1437.6886399434397,"arena_creative_writing_rating_upper":1462.1767735800763,"arena_creative_writing_vote_count":2718,"arena_creative_writing_date":"2026-10-15"}},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro (Preview)","org":"google","provider":"quartz","provider_display":"Quartz","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":65536,"pricing":{"input":2,"output":12,"cache_read":0.19999999999999998,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-19","knowledge_cutoff":"2025-01","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://ai.google.dev/gemini-api/docs/models","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.7,"coding_index":68.8,"agentic_index":8.2,"design_arena_best":{"category":"svg","elo":1283,"win_rate":67.8,"rank":12},"arena_text":1486.9094358879568,"arena_text_rank":19,"arena_text_rating_lower":1483.9491002818586,"arena_text_rating_upper":1489.869771494055,"arena_text_vote_count":127649,"arena_text_date":"2026-10-15","arena_creative_writing":1480.996930948638,"arena_creative_writing_rank":12,"arena_creative_writing_rating_lower":1475.677482894711,"arena_creative_writing_rating_upper":1486.3163790025653,"arena_creative_writing_vote_count":23619,"arena_creative_writing_date":"2026-10-15"}},{"id":"gemma-4-31b-it","name":"Gemma 4 31B IT","org":"google","provider":"consensusprotocol","provider_display":"Consensus Protocol","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":32768,"pricing":{"input":0.09999999999999999,"output":0.25,"cache_read":0.01,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"gemma-4-31b-it","name":"Gemma 4 31B IT","org":"google","provider":"runware","provider_display":"Runware","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":65536,"pricing":{"input":0.102,"output":0.29700000000000004,"cache_read":0.012,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"mimo-v2.6-flash","name":"MiMo V2.6 Flash","org":"xiaomi","provider":"consensusprotocol","provider_display":"Consensus Protocol","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":65536,"pricing":{"input":0.12,"output":0.25,"cache_read":0.0025,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"muse-spark-1.3-contributor","name":"Muse Spark 1.3 Contributor","org":"meta","provider":"meta-contributor","provider_display":"Meta Contributor","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":1048576,"pricing":{"input":0.09999999999999999,"output":0.19999999999999998,"cache_read":0.002,"cache_write":null},"modelsdev":{"base_url":"https://api.meta.ai/v1","model_id":"muse-spark-1.3-contributor","doc_url":"https://dev.meta.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-09-02","knowledge_cutoff":null,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","org":"meta","provider":"meta-contributor","provider_display":"Meta Contributor","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":0.09999999999999999,"output":0.19999999999999998,"cache_read":0.002,"cache_write":null},"modelsdev":{"base_url":"https://api.meta.ai/v1","model_id":"muse-spark-1.2-contributor","doc_url":"https://dev.meta.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-08-05","knowledge_cutoff":null,"description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v3.2","name":"DeepSeek V3.2","org":"deepseek","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":160000,"max_completion_tokens":32768,"pricing":{"input":0.28,"output":0.42,"cache_read":0.056,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","org":"deepseek","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":393216,"pricing":{"input":1.32,"output":3.9600000000000004,"cache_read":0.044,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","org":"deepseek","provider":"canopywave","provider_display":"CanopyWave","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":393216,"pricing":{"input":1.74,"output":3.48,"cache_read":0.01,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","org":"deepseek","provider":"runware","provider_display":"Runware","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":384000,"pricing":{"input":0.961,"output":1.922,"cache_read":0.079,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","org":"deepseek","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":393216,"pricing":{"input":0.44,"output":1.32,"cache_read":0.014,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","org":"deepseek","provider":"ranoai","provider_display":"RanoAI","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":393216,"pricing":{"input":0.14,"output":0.28,"cache_read":0.028,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","org":"deepseek","provider":"canopywave","provider_display":"CanopyWave","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":393216,"pricing":{"input":0.14,"output":0.28,"cache_read":0.03,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","org":"deepseek","provider":"consensusprotocol","provider_display":"Consensus Protocol","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":131072,"pricing":{"input":0.09999999999999999,"output":0.19999999999999998,"cache_read":0.005,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","org":"deepseek","provider":"runware","provider_display":"Runware","quantization":null,"discount":0,"context_length":1050000,"max_completion_tokens":384000,"pricing":{"input":0.07600000000000001,"output":0.153,"cache_read":0.014,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","org":"deepseek","provider":"luminal","provider_display":"Luminal","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":393216,"pricing":{"input":0.135,"output":0.54,"cache_read":0.0027,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","org":"deepseek","provider":"reka-ai","provider_display":"Reka Ai","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":393216,"pricing":{"input":0.15,"output":0.6,"cache_read":0.009,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","org":"deepseek","provider":"scx-ai-gp","provider_display":"SCX.ai GP","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":393216,"pricing":{"input":0.15,"output":0.6,"cache_read":0.01,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","org":"deepseek","provider":"runware","provider_display":"Runware","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":393216,"pricing":{"input":0.15,"output":0.6,"cache_read":0.01,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","org":"deepseek","provider":"consensusprotocol","provider_display":"Consensus Protocol","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":393216,"pricing":{"input":0.15,"output":0.55,"cache_read":0.005,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","org":"deepseek","provider":"reka-ai","provider_display":"Reka Ai","quantization":null,"discount":0,"context_length":1056784,"max_completion_tokens":393216,"pricing":{"input":0.19999999999999998,"output":0.7999999999999999,"cache_read":0.01,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","org":"deepseek","provider":"runware","provider_display":"Runware","quantization":null,"discount":0,"context_length":1056784,"max_completion_tokens":1048576,"pricing":{"input":0.15,"output":0.6,"cache_read":0.01,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","org":"deepseek","provider":"entrim","provider_display":"Entrim","quantization":null,"discount":0,"context_length":1056784,"max_completion_tokens":131072,"pricing":{"input":0.19999999999999998,"output":0.7999999999999999,"cache_read":0.005,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","org":"deepseek","provider":"sciforium","provider_display":"Sciforium","quantization":null,"discount":0,"context_length":1056784,"max_completion_tokens":131072,"pricing":{"input":0.15,"output":0.6,"cache_read":0.003,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"minimax-m3","name":"MiniMax M3","org":"minimax","provider":"consensusprotocol","provider_display":"Consensus Protocol","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":0.28,"output":1.1,"cache_read":0.049999999999999996,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-01","knowledge_cutoff":null,"description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax-m2.7","name":"MiniMax M2.7","org":"minimax","provider":"scx-ai","provider_display":"SCX.ai","quantization":null,"discount":0,"context_length":204800,"max_completion_tokens":196608,"pricing":{"input":0.48,"output":1.79,"cache_read":0.049999999999999996,"cache_write":null},"modelsdev":{"base_url":"https://api.scx.ai/v1","model_id":"MiniMax-M2.7","doc_url":"https://platform.scx.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-03-18","knowledge_cutoff":null,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":52.6,"agentic_index":15.3,"design_arena_best":{"category":"website","elo":1241,"win_rate":51.3,"rank":49},"arena_text":1415.0035341569967,"arena_text_rank":140,"arena_text_rating_lower":1411.653118390283,"arena_text_rating_upper":1418.3539499237102,"arena_text_vote_count":84977,"arena_text_date":"2026-10-15","arena_creative_writing":1363.9436635426205,"arena_creative_writing_rank":165,"arena_creative_writing_rating_lower":1357.8156580924347,"arena_creative_writing_rating_upper":1370.071668992806,"arena_creative_writing_vote_count":14495,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k2.6","name":"Kimi K2.6","org":"moonshot","provider":"canopywave","provider_display":"CanopyWave","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":32768,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k2.6","name":"Kimi K2.6","org":"moonshot","provider":"runware","provider_display":"Runware","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":131072,"pricing":{"input":0.6,"output":3.05,"cache_read":0.13,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","org":"moonshot","provider":"scx-ai-gp","provider_display":"SCX.ai GP","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":262144,"pricing":{"input":0.737,"output":3.08,"cache_read":0.143,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"kimi-k3","name":"Kimi K3","org":"moonshot","provider":"runpod","provider_display":"Runpod","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":1048576,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k3","name":"Kimi K3","org":"moonshot","provider":"canopywave","provider_display":"CanopyWave","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":1048576,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k3","name":"Kimi K3","org":"moonshot","provider":"runware","provider_display":"Runware","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":1048576,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k3","name":"Kimi K3","org":"moonshot","provider":"scx-ai-gp","provider_display":"SCX.ai GP","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":1048576,"pricing":{"input":3.1350000000000002,"output":15.675,"cache_read":0.319,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3-14b","name":"Qwen3 14B","org":"qwen","provider":"greenference","provider_display":"Greenference","quantization":null,"discount":0,"context_length":16384,"max_completion_tokens":8192,"pricing":{"input":0.07600000000000001,"output":0.228,"cache_read":null,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":13.8,"agentic_index":0.9,"design_arena_best":null}},{"id":"qwen3-32b","name":"Qwen3 32B","org":"qwen","provider":"scx-ai","provider_display":"SCX.ai","quantization":null,"discount":0,"context_length":32768,"max_completion_tokens":8192,"pricing":{"input":0.36,"output":0.87,"cache_read":null,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":15.3,"agentic_index":0.9,"design_arena_best":null,"arena_text":1346.8054887198539,"arena_text_rank":223,"arena_text_rating_lower":1337.3482173985908,"arena_text_rating_upper":1356.2627600411167,"arena_text_vote_count":3926,"arena_text_date":"2026-10-15","arena_creative_writing":1303.7112252714267,"arena_creative_writing_rank":233,"arena_creative_writing_rating_lower":1281.09210485787,"arena_creative_writing_rating_upper":1326.330345684983,"arena_creative_writing_vote_count":616,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3B","org":"qwen","provider":"greenference","provider_display":"Greenference","quantization":null,"discount":0,"context_length":8192,"max_completion_tokens":4096,"pricing":{"input":0.095,"output":0.28500000000000003,"cache_read":null,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04-28","knowledge_cutoff":null,"description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":967,"win_rate":39,"rank":121},"arena_text":1326.720438450228,"arena_text_rank":250,"arena_text_rating_lower":1321.9721027866842,"arena_text_rating_upper":1331.4687741137718,"arena_text_vote_count":26157,"arena_text_date":"2026-10-15","arena_creative_writing":1283.6416183810823,"arena_creative_writing_rank":260,"arena_creative_writing_rating_lower":1273.1820766690896,"arena_creative_writing_rating_upper":1294.1011600930747,"arena_creative_writing_vote_count":3340,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3.8-max","name":"Qwen3.8 Max","org":"qwen","provider":"scx-ai-gp","provider_display":"SCX.ai GP","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":131072,"pricing":{"input":1.54,"output":4.631,"cache_read":0.198,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-03","knowledge_cutoff":null,"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":45.4,"coding_index":76.2,"agentic_index":56,"design_arena_best":null,"arena_text":1482.3530183862679,"arena_text_rank":24,"arena_text_rating_lower":1477.3762943638942,"arena_text_rating_upper":1487.3297424086413,"arena_text_vote_count":27766,"arena_text_date":"2026-10-15","arena_creative_writing":1468.9997777918718,"arena_creative_writing_rank":19,"arena_creative_writing_rating_lower":1459.9936527553632,"arena_creative_writing_rating_upper":1478.0059028283804,"arena_creative_writing_vote_count":5471,"arena_creative_writing_date":"2026-10-15"}},{"id":"seed-1-6-250615","name":"Seed 1.6 (250615)","org":"bytedance","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":256000,"max_completion_tokens":null,"pricing":{"input":0.25,"output":2,"cache_read":0.049999999999999996,"cache_write":null},"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"seed-1-6-flash-250715","name":"Seed 1.6 Flash (250715)","org":"bytedance","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":256000,"max_completion_tokens":null,"pricing":{"input":0.07,"output":0.3,"cache_read":0.015,"cache_write":null},"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"seed-1-8-251228","name":"Seed 1.8 (251228)","org":"bytedance","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":256000,"max_completion_tokens":null,"pricing":{"input":0.25,"output":2,"cache_read":0.049999999999999996,"cache_write":null},"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"seed-2-0-pro-260328","name":"Seed 2.0 Pro (260328)","org":"bytedance","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":131072,"pricing":{"input":0.5,"output":3,"cache_read":0.09999999999999999,"cache_write":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"seed-2-0-lite-260428","name":"Seed 2.0 Lite (260428)","org":"bytedance","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":131072,"pricing":{"input":0.25,"output":2,"cache_read":0.049999999999999996,"cache_write":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"seed-2-0-mini-260428","name":"Seed 2.0 Mini (260428)","org":"bytedance","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":131072,"pricing":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.02,"cache_write":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"seed-2-0-code-preview-260328","name":"Seed 2.0 Code Preview (260328)","org":"bytedance","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":131072,"pricing":{"input":0.5,"output":3,"cache_read":0.09999999999999999,"cache_write":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","org":"z-ai","provider":"entrim","provider_display":"Entrim","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":128000,"pricing":{"input":0.09999999999999999,"output":0.35,"cache_read":0.0175,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","org":"z-ai","provider":"greenference","provider_display":"Greenference","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":0.14,"output":0.49,"cache_read":0.028,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","org":"z-ai","provider":"reka-ai","provider_display":"Reka Ai","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":262144,"pricing":{"input":0.11,"output":0.33,"cache_read":0.027,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","org":"z-ai","provider":"consensusprotocol","provider_display":"Consensus Protocol","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":128000,"pricing":{"input":0.09999999999999999,"output":0.25,"cache_read":0.01,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","org":"z-ai","provider":"runware","provider_display":"Runware","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","org":"z-ai","provider":"scx-ai-gp","provider_display":"SCX.ai GP","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":0.088,"output":0.25,"cache_read":0.024999999999999998,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3","name":"GLM-5.3","org":"z-ai","provider":"entrim","provider_display":"Entrim","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":128000,"pricing":{"input":0.5,"output":2,"cache_read":0.15,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3","name":"GLM-5.3","org":"z-ai","provider":"runware","provider_display":"Runware","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":1.2,"output":4,"cache_read":0.19999999999999998,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3","name":"GLM-5.3","org":"z-ai","provider":"reka-ai","provider_display":"Reka Ai","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":262144,"pricing":{"input":0.44999999999999996,"output":1.7999999999999998,"cache_read":0.135,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3","name":"GLM-5.3","org":"z-ai","provider":"scx-ai-gp","provider_display":"SCX.ai GP","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":128000,"pricing":{"input":0.9239999999999999,"output":2.904,"cache_read":0.1716,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.2","name":"GLM-5.2","org":"z-ai","provider":"canopywave","provider_display":"CanopyWave","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":32768,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.2","name":"GLM-5.2","org":"z-ai","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":128000,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.2","name":"GLM-5.2","org":"z-ai","provider":"scx-ai-gp","provider_display":"SCX.ai GP","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"pricing":{"input":0.605,"output":2.1229999999999998,"cache_read":0.154,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.2","name":"GLM-5.2","org":"z-ai","provider":"runware","provider_display":"Runware","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":128000,"pricing":{"input":0.7999999999999999,"output":2.5500000000000003,"cache_read":0.16,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-4.7","name":"GLM-4.7","org":"z-ai","provider":"bytedance","provider_display":"ByteDance","quantization":null,"discount":0,"context_length":204800,"max_completion_tokens":128000,"pricing":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.2,"coding_index":45.3,"agentic_index":null,"design_arena_best":{"category":"website","elo":1224,"win_rate":55.3,"rank":57},"arena_text":1441.3266291777354,"arena_text_rank":95,"arena_text_rating_lower":1435.2694154856003,"arena_text_rating_upper":1447.3838428698703,"arena_text_vote_count":12253,"arena_text_date":"2026-10-15","arena_creative_writing":1404.7365646711344,"arena_creative_writing_rank":102,"arena_creative_writing_rating_lower":1391.4905429408939,"arena_creative_writing_rating_upper":1417.9825864013746,"arena_creative_writing_vote_count":1960,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-fast","name":"GLM 5.3 Fast","org":"z-ai","provider":"scx-ai-gp","provider_display":"SCX.ai GP","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":128000,"pricing":{"input":2.8,"output":8.8,"cache_read":0.56,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3.6-27b","name":"Qwen3.6 27B","org":"qwen","provider":"greenference","provider_display":"Greenference","quantization":null,"discount":0,"context_length":16384,"max_completion_tokens":8192,"pricing":{"input":0.15,"output":1.35,"cache_read":null,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":21.4,"coding_index":53.7,"agentic_index":18.5,"design_arena_best":null}},{"id":"reka-edge-2603","name":"Reka Edge 2603","org":"reka-ai","provider":"reka-ai","provider_display":"Reka Ai","quantization":null,"discount":0,"context_length":16384,"max_completion_tokens":16384,"pricing":{"input":0.09999999999999999,"output":0.09999999999999999,"cache_read":null,"cache_write":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"glm-5.2-fast","name":"GLM-5.2 Turbo","org":"z-ai","provider":"scx-ai-gp","provider_display":"SCX.ai GP","quantization":null,"discount":0,"context_length":1000000,"max_completion_tokens":131072,"pricing":{"input":2.156,"output":6.776,"cache_read":0.429,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"Qwen3.8-27B","name":"Qwen3.8 27B","org":"qwen","provider":"consensusprotocol","provider_display":"Consensus Protocol","quantization":null,"discount":0,"context_length":262000,"max_completion_tokens":null,"pricing":{"input":0.08,"output":0.35,"cache_read":0.049999999999999996,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","org":"z-ai","provider":"runanywhere","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"input_modalities":["text"],"pricing":{"input":0.272,"output":0.65,"cache_read":0.076,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","org":"deepseek","provider":"runanywhere","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":65536,"input_modalities":["text","image"],"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k3","name":"Kimi K3","org":"moonshot","provider":"runanywhere","quantization":"mxfp4","discount":0,"context_length":1048576,"max_completion_tokens":65536,"input_modalities":["text","image"],"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash-fast","name":"DeepSeek V4.1 Flash (Fast)","org":"deepseek","provider":"runanywhere","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":65536,"input_modalities":["text","image"],"pricing":{"input":0.6,"output":2.4,"cache_read":0.014,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-fast","name":"GLM-5.3 (Fast)","org":"z-ai","provider":"runanywhere","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"input_modalities":["text"],"pricing":{"input":2.1,"output":6.6,"cache_read":0.39,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-pro-fast","name":"DeepSeek V4 Pro (Fast)","org":"deepseek","provider":"runanywhere","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":65536,"input_modalities":["text"],"pricing":{"input":1.91,"output":3.83,"cache_read":0.16,"cache_write":null},"zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","org":"deepseek","provider":"runanywhere","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":65536,"input_modalities":["text"],"pricing":{"input":0.44,"output":1.32,"cache_read":0.014,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"minimax-m3","name":"MiniMax M3","org":"minimax","provider":"runanywhere","quantization":"bf16","discount":0,"context_length":524287,"max_completion_tokens":131072,"input_modalities":["text"],"pricing":{"input":0.33,"output":1.32,"cache_read":0.066,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-01","knowledge_cutoff":null,"description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","org":"deepseek","provider":"runanywhere","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":65536,"input_modalities":["text"],"pricing":{"input":0.375,"output":1.5,"cache_read":0.008,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek-v4-flash-0731","name":"deepseek-v4-flash-0731","org":"deepseek","provider":"engy","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":null,"input_modalities":["text"],"pricing":{"input":0.045,"output":0.09,"cache_read":0.009,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek-v4.1-flash","name":"deepseek-v4.1-flash","org":"deepseek","provider":"engy","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":null,"input_modalities":["image","text"],"pricing":{"input":0.03,"output":0.12,"cache_read":0.006,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash-1017","name":"deepseek-v4.1-flash-1017","org":"deepseek","provider":"engy","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":null,"input_modalities":["image","text"],"pricing":{"input":0.03,"output":0.12,"cache_read":0.006,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"glm-5.2","name":"glm-5.2","org":"z-ai","provider":"engy","quantization":null,"discount":0,"context_length":262144,"max_completion_tokens":null,"input_modalities":["text"],"pricing":{"input":0.68,"output":1.5,"cache_read":0.18,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3","name":"glm-5.3","org":"z-ai","provider":"engy","quantization":null,"discount":0,"context_length":327680,"max_completion_tokens":null,"input_modalities":["text"],"pricing":{"input":0.98,"output":3.08,"cache_read":0.18,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"glm-5.3-flash","org":"z-ai","provider":"engy","quantization":null,"discount":0,"context_length":327680,"max_completion_tokens":null,"input_modalities":["image","text"],"pricing":{"input":0.135,"output":0.45,"cache_read":0.027,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k3","name":"kimi-k3","org":"moonshot","provider":"engy","quantization":null,"discount":0,"context_length":1113088,"max_completion_tokens":null,"input_modalities":["image","text"],"pricing":{"input":1.95,"output":9.75,"cache_read":0.195,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3.6-35b-a3b","name":"qwen3.6-35b-a3b","org":"qwen","provider":"engy","quantization":null,"discount":0,"context_length":208192,"max_completion_tokens":null,"input_modalities":["text"],"pricing":{"input":0.045,"output":0.3,"cache_read":0.015,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"qwen3.8-27b","name":"qwen3.8-27b","org":"qwen","provider":"engy","quantization":null,"discount":0,"context_length":1001536,"max_completion_tokens":null,"input_modalities":["image","text"],"pricing":{"input":0.045,"output":0.32,"cache_read":0.015,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","org":"deepseek","provider":"openscale","quantization":null,"discount":0,"context_length":1048568,"max_completion_tokens":384000,"input_modalities":["text","image"],"pricing":{"input":0.06,"output":0.24,"cache_read":0.003,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","org":"z-ai","provider":"openscale","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"input_modalities":["text","image"],"pricing":{"input":0.12,"output":0.4,"cache_read":0.024,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"glimmer-30b","name":"Muse: Muse Glimmer 30B","org":"muse","provider":"openscale","quantization":null,"discount":0,"context_length":131072,"max_completion_tokens":16384,"input_modalities":["text"],"pricing":{"input":0.3,"output":1.2,"cache_read":0.04,"cache_write":null},"zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","org":"deepseek","provider":"openscale","quantization":null,"discount":0,"context_length":1048568,"max_completion_tokens":384000,"input_modalities":["text","image"],"pricing":{"input":0.06,"output":0.24,"cache_read":0.003,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek-v4.1-flash-0910","name":"DeepSeek: DeepSeek V4.1 Flash 0910","org":"deepseek","provider":"openscale","quantization":null,"discount":0,"context_length":1048568,"max_completion_tokens":384000,"input_modalities":["text","image"],"pricing":{"input":0.06,"output":0.24,"cache_read":0.003,"cache_write":null},"zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"glm-5.3-flash-0828","name":"Z.ai: GLM 5.3 Flash 0828","org":"z-ai","provider":"openscale","quantization":null,"discount":0,"context_length":1048576,"max_completion_tokens":131072,"input_modalities":["text","image"],"pricing":{"input":0.12,"output":0.4,"cache_read":0.024,"cache_write":null},"zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v4.1-flash:fast","name":"DeepSeek: DeepSeek V4.1 Flash (fast)","org":"deepseek","provider":"openscale","quantization":null,"discount":0,"context_length":1048568,"max_completion_tokens":384000,"input_modalities":["text","image"],"pricing":{"input":0.28,"output":1.1,"cache_read":0.028,"cache_write":null},"zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash-1017:fast","name":"DeepSeek: DeepSeek V4.1 Flash 1017 (fast)","org":"deepseek","provider":"openscale","quantization":null,"discount":0,"context_length":1048568,"max_completion_tokens":384000,"input_modalities":["text","image"],"pricing":{"input":0.28,"output":1.1,"cache_read":0.028,"cache_write":null},"zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek-v4.1-flash-0910:fast","name":"DeepSeek: DeepSeek V4.1 Flash 0910 (fast)","org":"deepseek","provider":"openscale","quantization":null,"discount":0,"context_length":1048568,"max_completion_tokens":384000,"input_modalities":["text","image"],"pricing":{"input":0.28,"output":1.1,"cache_read":0.028,"cache_write":null},"zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","provider":"zro","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.3,"output":1.1,"cache_read":0.01,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3","name":"GLM-5.3","provider":"zro","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.4,"output":4.2,"cache_read":0.3,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","provider":"zro","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.15,"output":0.5,"cache_read":0.04,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"dolly1-security","name":"Dolly 1 Security","provider":"zro","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.45,"output":1.5,"cache_read":0.12,"cache_write":null},"org":"zro","open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"dolly2-security","name":"Dolly 2 Security","provider":"zro","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2.1,"output":6.3,"cache_read":0.45,"cache_write":null},"org":"zro","open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"particle-ai/particle-1","name":"Particle AI: Particle-1","provider":"particle-ai","provider_display":"Particle AI","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.25,"output":1,"cache_read":0.03,"cache_write":null},"org":"particle-ai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-terra-pro:flex","name":"OpenAI: GPT-6.1 Terra Pro (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":96.29629629629629,"pricing":{"input":0.5,"output":2.5,"cache_read":0.024999999999999998,"cache_write":0.625},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-terra-pro","name":"OpenAI: GPT-6.1 Terra Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":1,"output":5,"cache_read":0.049999999999999996,"cache_write":1.25},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-terra-pro","name":"OpenAI: GPT-6.1 Terra Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","verbosity","response_format","seed","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.2,"output":6,"cache_read":0.06,"cache_write":1.5},"org":"openai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-terra-pro:fast","name":"OpenAI: GPT-6.1 Terra Pro (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-terra-pro:batch","name":"OpenAI: GPT-6.1 Terra Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.5,"output":2.5,"cache_read":0.024999999999999998,"cache_write":0.625},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-terra:flex","name":"OpenAI: GPT-6.1 Terra (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":95.43834640057021,"pricing":{"input":0.5,"output":2.5,"cache_read":0.024999999999999998,"cache_write":0.625},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6.1-terra","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-10-26","knowledge_cutoff":"2026-06-01","description":"Fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":51,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"openai/gpt-6.1-terra","name":"OpenAI: GPT-6.1 Terra","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":1,"output":5,"cache_read":0.049999999999999996,"cache_write":1.25},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":2,"output":7.5,"cache_read":0.1,"cache_write":2.5},{"above_tokens":272000,"input":2,"output":7.5,"cache_read":0.1,"cache_write":2.5}],"modelsdev":{"base_url":null,"model_id":"gpt-6.1-terra","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-10-26","knowledge_cutoff":"2026-06-01","description":"Fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":51,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"openai/gpt-6.1-terra","name":"OpenAI: GPT-6.1 Terra","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","verbosity","response_format","seed","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":1.2,"output":6,"cache_read":0.06,"cache_write":1.5},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-6.1-terra","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-10-26","knowledge_cutoff":"2026-06-01","description":"Fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":51,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"openai/gpt-6.1-terra:fast","name":"OpenAI: GPT-6.1 Terra (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6.1-terra","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-10-26","knowledge_cutoff":"2026-06-01","description":"Fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":51,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"openai/gpt-6.1-terra:batch","name":"OpenAI: GPT-6.1 Terra (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":0.5,"output":2.5,"cache_read":0.024999999999999998,"cache_write":0.625},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6.1-terra","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-10-26","knowledge_cutoff":"2026-06-01","description":"Fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":51,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"moonshotai/kimi-k3.1-pro","name":"MoonshotAI: Kimi K3.1 Pro","provider":"moonshot","provider_display":"Moonshot AI","quantization":"mxfp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","frequency_penalty","presence_penalty","structured_outputs","response_format","tool_choice","tools","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2},"org":"moonshot","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.moonshot.ai/v1","model_id":"kimi-k3.1-pro","doc_url":"https://platform.moonshot.ai/docs/api/chat","confidence":"high","source":"models.dev","release_date":"2026-10-23","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":46,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1451,"win_rate":72.7,"rank":2}}},{"id":"moonshotai/kimi-k3.1-pro:highspeed","name":"MoonshotAI: Kimi K3.1 Pro (highspeed)","provider":"moonshot","provider_display":"Moonshot AI","quantization":"mxfp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","frequency_penalty","presence_penalty","structured_outputs","response_format","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":4,"output":20,"cache_read":0.19999999999999998,"cache_write":2},"org":"moonshot","subscription":true,"modelsdev":{"base_url":"https://api.moonshot.ai/v1","model_id":"kimi-k3.1-pro","doc_url":"https://platform.moonshot.ai/docs/api/chat","confidence":"medium","source":"models.dev","release_date":"2026-10-23","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":46,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1451,"win_rate":72.7,"rank":2}}},{"id":"minimax/minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.1,"context_length":1000000,"max_completion_tokens":512000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.54504094631483,"pricing":{"input":0.135,"output":0.54,"cache_read":0.0135,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"minimax/minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.05,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.85443959243085,"pricing":{"input":0.14250000000000002,"output":0.5700000000000001,"cache_read":0.01425,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"minimax/minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/minimax-m3p1-flash","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"minimax/minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","provider":"inferencenet","provider_display":"InferenceNet","quantization":"fp4","discount":0,"context_length":1000000,"max_completion_tokens":524288,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","logit_bias","response_format","structured_outputs","repetition_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.98488664987406,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"minimax/minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"minimax-m3.1-flash","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"minimax/minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","provider":"novita","provider_display":"Novita","quantization":"fp16","discount":0,"context_length":1000000,"max_completion_tokens":524288,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.33774834437085,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"minimax/minimax-m3.1-flash","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"minimax/minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","provider":"modelrun","provider_display":"ModelRun","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","presence_penalty","repetition_penalty","frequency_penalty","stop","top_p","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.78932584269663,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"minimax/minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":524288,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"minimax/minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.5729537366548,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"minimax/minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":524288,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"minimax","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"morph","provider_display":"Morph","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","tools","tool_choice","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.86111111111111,"pricing":{"input":0.044,"output":0.38299999999999995,"cache_read":0.004,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"openinference","provider_display":"OpenInference","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","stop","seed","structured_outputs","tools","tool_choice","response_format","top_p","top_k","min_p","logit_bias","frequency_penalty","presence_penalty","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.054200000000000005,"output":1.64,"cache_read":0.0537,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"reka","provider_display":"Reka","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":94.6576373212942,"pricing":{"input":0.06,"output":0.6,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"relace","provider_display":"Relace","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","stop","max_tokens","logit_bias","frequency_penalty","presence_penalty","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.07,"output":0.5,"cache_read":0.008,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017:flex","name":"DeepSeek: DeepSeek V4.1 Flash 1017 (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0.51,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":91.25,"pricing":{"input":0.0784,"output":0.2352,"cache_read":0.0023520000000000004,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"inferencenet","provider_display":"InferenceNet","quantization":"fp8","discount":0,"context_length":1040000,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","response_format","structured_outputs","repetition_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.08,"output":0.55,"cache_read":0.008,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.6,"cache_read":0.003,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/deepseek-ai/deepseek-v4.1-flash-1017","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"sail-research","provider_display":"Sail Research","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","presence_penalty","seed","stop","temperature","top_k","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.101,"output":0.15,"cache_read":0.006735,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"decart","provider_display":"Decart","quantization":"fp4","discount":0.18,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":92.00278164116828,"pricing":{"input":0.123,"output":0.492,"cache_read":0.0024600000000000004,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017:priority","name":"DeepSeek: DeepSeek V4.1 Flash 1017 (priority)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0.51,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.14700000000000002,"output":0.441,"cache_read":0.00441,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.465,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.14980000000000002,"output":0.60455,"cache_read":0.0032099999999999997,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.5,"context_length":1024000,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.6,"cache_read":0.003,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"deepseek","provider_display":"DeepSeek","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logprobs","top_logprobs","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.6,"cache_read":0.003,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"makora","provider_display":"Makora","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"ionstream","provider_display":"Ionstream","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","frequency_penalty","logit_bias","presence_penalty","seed","stop","top_k","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.165,"output":0.49500000000000005,"cache_read":0.010499999999999999,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":94.4405348346235,"pricing":{"input":0.165,"output":0.66,"cache_read":0.016499999999999997,"cache_write":null},"org":"deepseek","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"modelrun","provider_display":"ModelRun","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","presence_penalty","repetition_penalty","frequency_penalty","stop","top_p","structured_outputs","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.58915365653246,"pricing":{"input":0.16999999999999998,"output":0.67,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.18,"output":0.72,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"deepseek-v4.1-flash-1017","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.4,"context_length":1048575,"max_completion_tokens":943717,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.60356865787432,"pricing":{"input":0.18,"output":0.72,"cache_read":0.0036,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice","parallel_tool_calls","logprobs","top_logprobs","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.195,"output":0.66,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.34532374100719,"pricing":{"input":0.195,"output":0.78,"cache_read":0.0039000000000000003,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.35,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.195,"output":0.78,"cache_read":0.0039000000000000003,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-v4.1-flash-1017","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":93.50473612990527,"pricing":{"input":0.19999999999999998,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.21,"output":0.84,"cache_read":0.004200000000000001,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/deepseek-v4p1-flash-1017","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"particle-ai","provider_display":"Particle AI","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.25,"output":1,"cache_read":0.03,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"modal","provider_display":"Modal","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","stop","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.25,"output":1,"cache_read":0.005,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"crusoe","provider_display":"Crusoe","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.29,"output":1.2,"cache_read":0.007,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.0075,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"mistral","provider_display":"Mistral","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.49521203830369,"pricing":{"input":0.3,"output":1.2,"cache_read":0.007,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"primeintellect","provider_display":"PrimeIntellect","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","max_completion_tokens","temperature","top_p","top_k","stop","frequency_penalty","repetition_penalty","parallel_tool_calls","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"baseten","provider_display":"BaseTen","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.007,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-17","knowledge_cutoff":"2025-05","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1360,"win_rate":46.7,"rank":10}}},{"id":"elorian/glimpse","name":"Elorian: Glimpse","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":256000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":96.05633802816902,"pricing":{"input":0.6,"output":3,"cache_read":0.06,"cache_write":null},"org":"elorian","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"reflection/beam-1.0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","provider":"nebius","provider_display":"Nebius","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.94238683127571,"pricing":{"input":0.25,"output":1,"cache_read":0.049999999999999996,"cache_write":null},"org":"reflection","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-05","knowledge_cutoff":"2026-06-30","description":"Beam is a 501B-parameter MoE model with 23B active parameters built for coding, reasoning, and agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1226,"win_rate":43.9,"rank":56}}},{"id":"reflection/beam-1.0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.91796554552911,"pricing":{"input":0.3,"output":1,"cache_read":0.04,"cache_write":null},"org":"reflection","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-05","knowledge_cutoff":"2026-06-30","description":"Beam is a 501B-parameter MoE model with 23B active parameters built for coding, reasoning, and agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1226,"win_rate":43.9,"rank":56}}},{"id":"reflection/beam-1.0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.39999999999999997,"output":1.2,"cache_read":0.04,"cache_write":null},"org":"reflection","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-05","knowledge_cutoff":"2026-06-30","description":"Beam is a 501B-parameter MoE model with 23B active parameters built for coding, reasoning, and agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1226,"win_rate":43.9,"rank":56}}},{"id":"reflection/beam-1.0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","provider":"baseten","provider_display":"BaseTen","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.39999999999999997,"output":1.2,"cache_read":0.04,"cache_write":null},"org":"reflection","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-05","knowledge_cutoff":"2026-06-30","description":"Beam is a 501B-parameter MoE model with 23B active parameters built for coding, reasoning, and agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1226,"win_rate":43.9,"rank":56}}},{"id":"reflection/beam-1.0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.70370370370371,"pricing":{"input":0.39999999999999997,"output":1.2,"cache_read":0.04,"cache_write":null},"org":"reflection","zdr":true,"modelsdev":{"base_url":null,"model_id":"reflection/Beam-1.0-501B-A23B","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-10-05","knowledge_cutoff":"2026-06-30","description":"Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"Apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1226,"win_rate":43.9,"rank":56}}},{"id":"inception/mercury-3","name":"Inception: Mercury 3","provider":"inception","provider_display":"Inception","quantization":"unknown","discount":0.5,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","temperature","tools","tool_choice","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.65277777777779,"pricing":{"input":0.09999999999999999,"output":0.35,"cache_read":0.01,"cache_write":null},"org":"inception","zdr":true,"modelsdev":{"base_url":"https://api.inceptionlabs.ai/v1/","model_id":"mercury-3","doc_url":"https://docs.inceptionlabs.ai/get-started/models","confidence":"high","source":"models.dev","release_date":"2026-10-16","knowledge_cutoff":null,"description":"Inception's diffusion reasoning model for chat, multi-step problem solving, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1232,"win_rate":45.6,"rank":48}}},{"id":"prism-ml/ternary-bonsai-2-9b","name":"PrismML: Ternary Bonsai 2 9B","provider":"darkbloom","provider_display":"Darkbloom","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.42028985507247,"pricing":{"input":0.08,"output":0.13,"cache_read":0.04,"cache_write":null},"org":"prism-ml","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"moondream/moondream3-preview","name":"Moondream: Moondream 3 Preview","provider":"primeintellect","provider_display":"PrimeIntellect","quantization":"fp8","discount":0,"context_length":32000,"max_completion_tokens":4096,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","max_completion_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":2.5,"cache_read":null,"cache_write":null},"org":"moondream","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"moondream/moondream3.1-9b-a2b","name":"Moondream: Moondream 3.1","provider":"primeintellect","provider_display":"PrimeIntellect","quantization":"fp8","discount":0,"context_length":32000,"max_completion_tokens":4096,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","max_completion_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":97.36842105263158,"pricing":{"input":0.3,"output":2.5,"cache_read":null,"cache_write":null},"org":"moondream","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"meta/muse-spark-open","name":"Meta: Muse Spark Open","provider":"makora","provider_display":"Makora","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","min_p","structured_outputs","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":null},"org":"meta","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-15","knowledge_cutoff":"2026-01-04","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Muse Model License","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1350,"win_rate":58.7,"rank":5}}},{"id":"meta/muse-spark-open","name":"Meta: Muse Spark Open","provider":"modal","provider_display":"Modal","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","stop","max_tokens","response_format","structured_outputs","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://inference.us-west.modal.direct/v1","model_id":"meta-models/Muse-Spark-Open-816B-A42B","doc_url":"https://modal.com/docs/guide/endpoints","confidence":"medium","source":"models.dev","release_date":"2026-10-15","knowledge_cutoff":"2026-01-04","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"Muse Model License","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1350,"win_rate":58.7,"rank":5}}},{"id":"meta/muse-spark-open","name":"Meta: Muse Spark Open","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.49749582637729,"pricing":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":null,"model_id":"meta-models/Muse-Spark-Open-816B-A42B","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"medium","source":"models.dev","release_date":"2026-10-15","knowledge_cutoff":"2026-01-04","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"Muse Model License","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1350,"win_rate":58.7,"rank":5}}},{"id":"meta/muse-spark-open","name":"Meta: Muse Spark Open","provider":"nebius","provider_display":"Nebius","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","tools","tool_choice","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":80,"pricing":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"meta-models/muse-spark-open","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-10-15","knowledge_cutoff":"2026-01-04","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"Muse Model License","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1350,"win_rate":58.7,"rank":5}}},{"id":"meta/muse-spark-open","name":"Meta: Muse Spark Open","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/muse-spark-open","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-10-15","knowledge_cutoff":"2026-01-04","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Muse Model License","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1350,"win_rate":58.7,"rank":5}}},{"id":"meta/muse-spark-open","name":"Meta: Muse Spark Open","provider":"baseten","provider_display":"BaseTen","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","top_k","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-15","knowledge_cutoff":"2026-01-04","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Muse Model License","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1350,"win_rate":58.7,"rank":5}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","provider":"darkbloom","provider_display":"Darkbloom","quantization":"nvfp4","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":90.71925754060325,"pricing":{"input":0.06,"output":0.35,"cache_read":0.01,"cache_write":null},"org":"nvidia","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-15","knowledge_cutoff":null,"description":"NVIDIA vision-language reasoning model for coding, visual understanding, and agentic tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.tokenfactory.nebius.com/","reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"openmdw-1.1","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1169,"win_rate":35.2,"rank":82}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","provider":"crusoe","provider_display":"Crusoe","quantization":"bf16","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.25871015567087,"pricing":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.08,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-15","knowledge_cutoff":null,"description":"NVIDIA vision-language reasoning model for coding, visual understanding, and agentic tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.tokenfactory.nebius.com/","reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"openmdw-1.1","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1169,"win_rate":35.2,"rank":82}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","provider":"io-net","provider_display":"Io Net","quantization":"nvfp4","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":96.66666666666667,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":95.17579721995094,"pricing":{"input":0.15,"output":0.5,"cache_read":0.02,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-15","knowledge_cutoff":null,"description":"NVIDIA vision-language reasoning model for coding, visual understanding, and agentic tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.tokenfactory.nebius.com/","reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"openmdw-1.1","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1169,"win_rate":35.2,"rank":82}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93011879804332,"pricing":{"input":0.15,"output":0.5,"cache_read":0.02,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev":{"base_url":null,"model_id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"medium","source":"models.dev","release_date":"2026-10-15","knowledge_cutoff":null,"description":"NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"openmdw-1.1","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1169,"win_rate":35.2,"rank":82}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.91334488734836,"pricing":{"input":0.15,"output":0.5,"cache_read":0.02,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-15","knowledge_cutoff":null,"description":"NVIDIA vision-language reasoning model for coding, visual understanding, and agentic tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.tokenfactory.nebius.com/","reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"openmdw-1.1","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1169,"win_rate":35.2,"rank":82}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","provider":"coreweave","provider_display":"CoreWeave","quantization":"nvfp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.92217898832685,"pricing":{"input":0.15,"output":0.5,"cache_read":0.02,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-15","knowledge_cutoff":null,"description":"NVIDIA vision-language reasoning model for coding, visual understanding, and agentic tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.tokenfactory.nebius.com/","reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"openmdw-1.1","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1169,"win_rate":35.2,"rank":82}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","provider":"venice","provider_display":"Venice","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.69135802469135,"pricing":{"input":0.19999999999999998,"output":0.5,"cache_read":0.04,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-15","knowledge_cutoff":null,"description":"NVIDIA vision-language reasoning model for coding, visual understanding, and agentic tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.tokenfactory.nebius.com/","reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"openmdw-1.1","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1169,"win_rate":35.2,"rank":82}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","provider":"baseten","provider_display":"BaseTen","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":0.5,"cache_read":0.04,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-15","knowledge_cutoff":null,"description":"NVIDIA vision-language reasoning model for coding, visual understanding, and agentic tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.tokenfactory.nebius.com/","reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"openmdw-1.1","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1169,"win_rate":35.2,"rank":82}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","provider":"nebius","provider_display":"Nebius","quantization":"bf16","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":95.01510574018127,"pricing":{"input":0.3,"output":0.8999999999999999,"cache_read":0.06,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"nvidia/Nemotron-3.5-Super-VL","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-10-15","knowledge_cutoff":null,"description":"NVIDIA vision-language reasoning model for coding, visual understanding, and agentic tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"openmdw-1.1","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":13.6,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1169,"win_rate":35.2,"rank":82}}},{"id":"unbiased/pareto-26.10","name":"Pareto 26.10","provider":"unbiased","provider_display":"Unbiased","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":95.83333333333334,"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.92821249102656,"pricing":{"input":0.7999999999999999,"output":3.1999999999999997,"cache_read":0.03,"cache_write":null},"org":"unbiased","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"unbiased/pareto-26.9","name":"Pareto 26.9","provider":"unbiased","provider_display":"Unbiased","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":68.36158192090396,"pricing":{"input":2.5,"output":7.5,"cache_read":0.25,"cache_write":null},"org":"unbiased","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"liquid/lfm-2.5-24b-a2b","name":"LiquidAI: LFM2.5-24B-A2B","provider":"liquid","provider_display":"Liquid","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","max_completion_tokens","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.049999999999999996,"output":0.7,"cache_read":0.024999999999999998,"cache_write":null},"org":"liquid","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"google/gemini-4-argon:flex","name":"Google: Gemini 4 Argon (flex)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":5,"cache_read":0.049999999999999996,"cache_write":0.09375},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-4-argon","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-10-13","knowledge_cutoff":"2026-03","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"blender3d","elo":1407,"win_rate":68.8,"rank":1},"arena_text":1523.9035861299108,"arena_text_rank":1,"arena_text_rating_lower":1515.0853098239602,"arena_text_rating_upper":1532.721862435861,"arena_text_vote_count":4904,"arena_text_date":"2026-10-15","arena_creative_writing":1515.5911597344439,"arena_creative_writing_rank":2,"arena_creative_writing_rating_lower":1496.1119665065833,"arena_creative_writing_rating_upper":1535.0703529623042,"arena_creative_writing_vote_count":1057,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-4-argon","name":"Google: Gemini 4 Argon","provider":"google","provider_display":"Google","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":98.61111111111111,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":0.1875},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-4-argon","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-10-13","knowledge_cutoff":"2026-03","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"blender3d","elo":1407,"win_rate":68.8,"rank":1},"arena_text":1523.9035861299108,"arena_text_rank":1,"arena_text_rating_lower":1515.0853098239602,"arena_text_rating_upper":1532.721862435861,"arena_text_vote_count":4904,"arena_text_date":"2026-10-15","arena_creative_writing":1515.5911597344439,"arena_creative_writing_rank":2,"arena_creative_writing_rating_lower":1496.1119665065833,"arena_creative_writing_rating_upper":1535.0703529623042,"arena_creative_writing_vote_count":1057,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-4-argon:priority","name":"Google: Gemini 4 Argon (priority)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3.5999999999999996,"output":18,"cache_read":0.18,"cache_write":0.3375},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-4-argon","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-10-13","knowledge_cutoff":"2026-03","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"blender3d","elo":1407,"win_rate":68.8,"rank":1},"arena_text":1523.9035861299108,"arena_text_rank":1,"arena_text_rating_lower":1515.0853098239602,"arena_text_rating_upper":1532.721862435861,"arena_text_vote_count":4904,"arena_text_date":"2026-10-15","arena_creative_writing":1515.5911597344439,"arena_creative_writing_rank":2,"arena_creative_writing_rating_lower":1496.1119665065833,"arena_creative_writing_rating_upper":1535.0703529623042,"arena_creative_writing_vote_count":1057,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-4-argon:batch","name":"Google: Gemini 4 Argon (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1,"output":5,"cache_read":0.049999999999999996,"cache_write":0.1875},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-4-argon","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-10-13","knowledge_cutoff":"2026-03","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"blender3d","elo":1407,"win_rate":68.8,"rank":1},"arena_text":1523.9035861299108,"arena_text_rank":1,"arena_text_rating_lower":1515.0853098239602,"arena_text_rating_upper":1532.721862435861,"arena_text_vote_count":4904,"arena_text_date":"2026-10-15","arena_creative_writing":1515.5911597344439,"arena_creative_writing_rank":2,"arena_creative_writing_rating_lower":1496.1119665065833,"arena_creative_writing_rating_upper":1535.0703529623042,"arena_creative_writing_vote_count":1057,"arena_creative_writing_date":"2026-10-15"}},{"id":"scaledown/summarize","name":"ScaleDown: Summarize","provider":"scaledown","provider_display":"ScaleDown","quantization":"unknown","discount":0.2,"context_length":1000000,"max_completion_tokens":4000,"uptime_30m":100,"supported_parameters":["max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.04,"output":0,"cache_read":null,"cache_write":null},"org":"scaledown","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"scaledown/extract","name":"ScaleDown: Extract","provider":"scaledown","provider_display":"ScaleDown","quantization":"unknown","discount":0.2,"context_length":1000000,"max_completion_tokens":900000,"uptime_30m":100,"supported_parameters":["max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.04,"output":0,"cache_read":null,"cache_write":null},"org":"scaledown","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"meta/muse-wonder","name":"Meta: Muse Wonder","provider":"meta","provider_display":"Meta","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":4,"output":20,"cache_read":0.19999999999999998,"cache_write":null},"org":"meta","modelsdev":{"base_url":"https://api.meta.ai/v1","model_id":"muse-wonder-1.0","doc_url":"https://dev.meta.ai/docs","confidence":"medium","source":"models.dev","release_date":"2026-10-12","knowledge_cutoff":null,"description":"Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1442,"win_rate":61.5,"rank":3},"arena_text":1508.8795055977137,"arena_text_rank":2,"arena_text_rating_lower":1498.3089865891718,"arena_text_rating_upper":1519.4500246062555,"arena_text_vote_count":3247,"arena_text_date":"2026-10-15","arena_creative_writing":1485.0836058732257,"arena_creative_writing_rank":8,"arena_creative_writing_rating_lower":1461.9229281435232,"arena_creative_writing_rating_upper":1508.2442836029284,"arena_creative_writing_vote_count":710,"arena_creative_writing_date":"2026-10-15"}},{"id":"stepfun/step-5-preview","name":"StepFun: Step 5 Preview","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":0,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":85.71428571428571,"pricing":{"input":1,"output":2.7,"cache_read":0.09999999999999999,"cache_write":null},"org":"stepfun","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-16","knowledge_cutoff":null,"description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://novita.ai/docs/guides/introduction","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.5,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1447.2701609595606,"arena_text_rank":84,"arena_text_rating_lower":1439.7616339961178,"arena_text_rating_upper":1454.7786879230032,"arena_text_vote_count":7116,"arena_text_date":"2026-10-15","arena_creative_writing":1403.2020336131102,"arena_creative_writing_rank":104,"arena_creative_writing_rating_lower":1387.2084544088364,"arena_creative_writing_rating_upper":1419.195612817384,"arena_creative_writing_vote_count":1517,"arena_creative_writing_date":"2026-10-15"}},{"id":"stepfun/step-5-preview","name":"StepFun: Step 5 Preview","provider":"featherless","provider_display":"Featherless","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","min_p","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":94.11764705882352,"pricing":{"input":1,"output":2.7,"cache_read":0.09999999999999999,"cache_write":null},"org":"stepfun","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-16","knowledge_cutoff":null,"description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://novita.ai/docs/guides/introduction","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.5,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1447.2701609595606,"arena_text_rank":84,"arena_text_rating_lower":1439.7616339961178,"arena_text_rating_upper":1454.7786879230032,"arena_text_vote_count":7116,"arena_text_date":"2026-10-15","arena_creative_writing":1403.2020336131102,"arena_creative_writing_rank":104,"arena_creative_writing_rating_lower":1387.2084544088364,"arena_creative_writing_rating_upper":1419.195612817384,"arena_creative_writing_vote_count":1517,"arena_creative_writing_date":"2026-10-15"}},{"id":"stepfun/step-5-preview","name":"StepFun: Step 5 Preview","provider":"stepfun","provider_display":"StepFun","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","top_p","stop","frequency_penalty","logprobs","top_logprobs","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":false,"supports_implicit_caching":true,"max_prompt_tokens":1000000,"uptime_1d":100,"pricing":{"input":1,"output":2.7,"cache_read":0.09999999999999999,"cache_write":null},"org":"stepfun","modelsdev":{"base_url":"https://api.stepfun.com/v1","model_id":"step-5-preview","doc_url":"https://platform.stepfun.com/docs/zh/overview/concept","confidence":"high","source":"models.dev","release_date":"2026-09-16","knowledge_cutoff":null,"description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.5,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1447.2701609595606,"arena_text_rank":84,"arena_text_rating_lower":1439.7616339961178,"arena_text_rating_upper":1454.7786879230032,"arena_text_vote_count":7116,"arena_text_date":"2026-10-15","arena_creative_writing":1403.2020336131102,"arena_creative_writing_rank":104,"arena_creative_writing_rating_lower":1387.2084544088364,"arena_creative_writing_rating_upper":1419.195612817384,"arena_creative_writing_vote_count":1517,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","response_format","tool_choice","tools","verbosity","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.01,"cache_write":0.125},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1343,"win_rate":58.1,"rank":11}}},{"id":"anthropic/claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.01,"cache_write":0.125},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1343,"win_rate":58.1,"rank":11}}},{"id":"anthropic/claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.01,"cache_write":0.125},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1343,"win_rate":58.1,"rank":11}}},{"id":"anthropic/claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.86111111111111,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.01,"cache_write":0.125},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1343,"win_rate":58.1,"rank":11}}},{"id":"anthropic/claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.01,"cache_write":0.125},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1343,"win_rate":58.1,"rank":11}}},{"id":"anthropic/claude-haiku-5.5:batch","name":"Anthropic: Claude Haiku 5.5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.049999999999999996,"output":0.25,"cache_read":0.005,"cache_write":0.0625},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1343,"win_rate":58.1,"rank":11}}},{"id":"mistralai/mistral-large-4-0","name":"Mistral: Mistral Large 4","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.7,"output":2.0999999999999996,"cache_read":0.07,"cache_write":null},"org":"mistral","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.3,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1275,"win_rate":51,"rank":26}}},{"id":"inclusionai/ling-3.1-flash","name":"inclusionAI: Ling 3.1 Flash","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0.75,"context_length":1000000,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.78354978354979,"pricing":{"input":0.075,"output":0.22499999999999998,"cache_read":0.015,"cache_write":null},"org":"inclusionai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"inclusionai/ling-3.1-flash","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-09-29","knowledge_cutoff":null,"description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.1,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"openai/gpt-6.1-sol-pro:flex","name":"OpenAI: GPT-6.1 Sol Pro (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":94.11764705882352,"pricing":{"input":1,"output":5,"cache_read":0.049999999999999996,"cache_write":1.25},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-sol-pro","name":"OpenAI: GPT-6.1 Sol Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","verbosity","response_format","seed","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":88.70967741935483,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"openai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-sol-pro","name":"OpenAI: GPT-6.1 Sol Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-sol-pro:fast","name":"OpenAI: GPT-6.1 Sol Pro (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":4,"output":20,"cache_read":0.19999999999999998,"cache_write":5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-sol-pro:ultrafast","name":"OpenAI: GPT-6.1 Sol Pro (ultrafast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":12,"output":60,"cache_read":0.6,"cache_write":15},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-sol-pro:batch","name":"OpenAI: GPT-6.1 Sol Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1,"output":5,"cache_read":0.049999999999999996,"cache_write":1.25},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6.1-sol:flex","name":"OpenAI: GPT-6.1 Sol (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":95.34075104311543,"pricing":{"input":1,"output":5,"cache_read":0.049999999999999996,"cache_write":1.25},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6.1-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-29","knowledge_cutoff":"2026-04-30","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1437,"win_rate":59.7,"rank":4},"arena_text":1483.8469422064072,"arena_text_rank":22,"arena_text_rating_lower":1475.7115409166886,"arena_text_rating_upper":1491.982343496126,"arena_text_vote_count":6320,"arena_text_date":"2026-10-15","arena_creative_writing":1458.4355581436328,"arena_creative_writing_rank":30,"arena_creative_writing_rating_lower":1441.4558548127359,"arena_creative_writing_rating_upper":1475.4152614745296,"arena_creative_writing_vote_count":1419,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","verbosity","response_format","seed","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":85.97222222222223,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"openai","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":4,"output":15,"cache_read":0.2,"cache_write":5},{"above_tokens":272000,"input":4,"output":15,"cache_read":0.2,"cache_write":5}],"modelsdev":{"base_url":null,"model_id":"gpt-6.1-sol","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-09-29","knowledge_cutoff":"2026-04-30","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1437,"win_rate":59.7,"rank":4},"arena_text":1483.8469422064072,"arena_text_rank":22,"arena_text_rating_lower":1475.7115409166886,"arena_text_rating_upper":1491.982343496126,"arena_text_vote_count":6320,"arena_text_date":"2026-10-15","arena_creative_writing":1458.4355581436328,"arena_creative_writing_rank":30,"arena_creative_writing_rating_lower":1441.4558548127359,"arena_creative_writing_rating_upper":1475.4152614745296,"arena_creative_writing_vote_count":1419,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":4,"output":15,"cache_read":0.2,"cache_write":5},{"above_tokens":272000,"input":4,"output":15,"cache_read":0.2,"cache_write":5}],"modelsdev":{"base_url":null,"model_id":"gpt-6.1-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-09-29","knowledge_cutoff":"2026-04-30","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1437,"win_rate":59.7,"rank":4},"arena_text":1483.8469422064072,"arena_text_rank":22,"arena_text_rating_lower":1475.7115409166886,"arena_text_rating_upper":1491.982343496126,"arena_text_vote_count":6320,"arena_text_date":"2026-10-15","arena_creative_writing":1458.4355581436328,"arena_creative_writing_rank":30,"arena_creative_writing_rating_lower":1441.4558548127359,"arena_creative_writing_rating_upper":1475.4152614745296,"arena_creative_writing_vote_count":1419,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2.2,"output":11,"cache_read":0.11,"cache_write":2.75},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1437,"win_rate":59.7,"rank":4},"arena_text":1483.8469422064072,"arena_text_rank":22,"arena_text_rating_lower":1475.7115409166886,"arena_text_rating_upper":1491.982343496126,"arena_text_vote_count":6320,"arena_text_date":"2026-10-15","arena_creative_writing":1458.4355581436328,"arena_creative_writing_rank":30,"arena_creative_writing_rating_lower":1441.4558548127359,"arena_creative_writing_rating_upper":1475.4152614745296,"arena_creative_writing_vote_count":1419,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6.1-sol:fast","name":"OpenAI: GPT-6.1 Sol (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":4,"output":20,"cache_read":0.19999999999999998,"cache_write":5},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6.1-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-29","knowledge_cutoff":"2026-04-30","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1437,"win_rate":59.7,"rank":4},"arena_text":1483.8469422064072,"arena_text_rank":22,"arena_text_rating_lower":1475.7115409166886,"arena_text_rating_upper":1491.982343496126,"arena_text_vote_count":6320,"arena_text_date":"2026-10-15","arena_creative_writing":1458.4355581436328,"arena_creative_writing_rank":30,"arena_creative_writing_rating_lower":1441.4558548127359,"arena_creative_writing_rating_upper":1475.4152614745296,"arena_creative_writing_vote_count":1419,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6.1-sol:ultrafast","name":"OpenAI: GPT-6.1 Sol (ultrafast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":12,"output":60,"cache_read":0.6,"cache_write":15},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6.1-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-29","knowledge_cutoff":"2026-04-30","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1437,"win_rate":59.7,"rank":4},"arena_text":1483.8469422064072,"arena_text_rank":22,"arena_text_rating_lower":1475.7115409166886,"arena_text_rating_upper":1491.982343496126,"arena_text_vote_count":6320,"arena_text_date":"2026-10-15","arena_creative_writing":1458.4355581436328,"arena_creative_writing_rank":30,"arena_creative_writing_rating_lower":1441.4558548127359,"arena_creative_writing_rating_upper":1475.4152614745296,"arena_creative_writing_vote_count":1419,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6.1-sol:batch","name":"OpenAI: GPT-6.1 Sol (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":1,"output":5,"cache_read":0.049999999999999996,"cache_write":1.25},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6.1-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-29","knowledge_cutoff":"2026-04-30","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1437,"win_rate":59.7,"rank":4},"arena_text":1483.8469422064072,"arena_text_rank":22,"arena_text_rating_lower":1475.7115409166886,"arena_text_rating_upper":1491.982343496126,"arena_text_vote_count":6320,"arena_text_date":"2026-10-15","arena_creative_writing":1458.4355581436328,"arena_creative_writing_rank":30,"arena_creative_writing_rating_lower":1441.4558548127359,"arena_creative_writing_rating_upper":1475.4152614745296,"arena_creative_writing_vote_count":1419,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","response_format","tool_choice","tools","verbosity","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1412,"win_rate":62.2,"rank":2},"arena_text":1474.93871350729,"arena_text_rank":36,"arena_text_rating_lower":1467.1980477406435,"arena_text_rating_upper":1482.6793792739365,"arena_text_vote_count":6831,"arena_text_date":"2026-10-15","arena_creative_writing":1465.0929307618035,"arena_creative_writing_rank":22,"arena_creative_writing_rating_lower":1448.864057666361,"arena_creative_writing_rating_upper":1481.321803857246,"arena_creative_writing_vote_count":1532,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1412,"win_rate":62.2,"rank":2},"arena_text":1474.93871350729,"arena_text_rank":36,"arena_text_rating_lower":1467.1980477406435,"arena_text_rating_upper":1482.6793792739365,"arena_text_vote_count":6831,"arena_text_date":"2026-10-15","arena_creative_writing":1465.0929307618035,"arena_creative_writing_rank":22,"arena_creative_writing_rating_lower":1448.864057666361,"arena_creative_writing_rating_upper":1481.321803857246,"arena_creative_writing_vote_count":1532,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1412,"win_rate":62.2,"rank":2},"arena_text":1474.93871350729,"arena_text_rank":36,"arena_text_rating_lower":1467.1980477406435,"arena_text_rating_upper":1482.6793792739365,"arena_text_vote_count":6831,"arena_text_date":"2026-10-15","arena_creative_writing":1465.0929307618035,"arena_creative_writing_rank":22,"arena_creative_writing_rating_lower":1448.864057666361,"arena_creative_writing_rating_upper":1481.321803857246,"arena_creative_writing_vote_count":1532,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1412,"win_rate":62.2,"rank":2},"arena_text":1474.93871350729,"arena_text_rank":36,"arena_text_rating_lower":1467.1980477406435,"arena_text_rating_upper":1482.6793792739365,"arena_text_vote_count":6831,"arena_text_date":"2026-10-15","arena_creative_writing":1465.0929307618035,"arena_creative_writing_rank":22,"arena_creative_writing_rating_lower":1448.864057666361,"arena_creative_writing_rating_upper":1481.321803857246,"arena_creative_writing_vote_count":1532,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1412,"win_rate":62.2,"rank":2},"arena_text":1474.93871350729,"arena_text_rank":36,"arena_text_rating_lower":1467.1980477406435,"arena_text_rating_upper":1482.6793792739365,"arena_text_vote_count":6831,"arena_text_date":"2026-10-15","arena_creative_writing":1465.0929307618035,"arena_creative_writing_rank":22,"arena_creative_writing_rating_lower":1448.864057666361,"arena_creative_writing_rating_upper":1481.321803857246,"arena_creative_writing_vote_count":1532,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5.5:batch","name":"Anthropic: Claude Sonnet 5.5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1,"output":5,"cache_read":0.049999999999999996,"cache_write":1.25},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":54.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1412,"win_rate":62.2,"rank":2},"arena_text":1474.93871350729,"arena_text_rank":36,"arena_text_rating_lower":1467.1980477406435,"arena_text_rating_upper":1482.6793792739365,"arena_text_vote_count":6831,"arena_text_date":"2026-10-15","arena_creative_writing":1465.0929307618035,"arena_creative_writing_rank":22,"arena_creative_writing_rating_lower":1448.864057666361,"arena_creative_writing_rating_upper":1481.321803857246,"arena_creative_writing_vote_count":1532,"arena_creative_writing_date":"2026-10-15"}},{"id":"perceptron/perceptron-mk1.5","name":"Perceptron: Perceptron Mk1.5","provider":"perceptron","provider_display":"Perceptron","quantization":"unknown","discount":0,"context_length":36864,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":1.5,"cache_read":null,"cache_write":null},"org":"perceptron","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"fireworks/ember-1","name":"Fireworks: Ember-1","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"fireworks","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/ember-1","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":null,"description":"Specialized model from Fireworks built on Kimi K3, producing shorter reasoning traces with approximately 40% fewer tokens while maintaining comparable quality","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"z-ai/glm-5.3-prime","name":"Z.ai: GLM 5.3 Prime","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.8,"output":8.8,"cache_read":0.56,"cache_write":null},"org":"z-ai","subscription":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3.8-max-prime","name":"Qwen: Qwen3.8 Max Prime","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":983616,"uptime_1d":100,"pricing":{"input":4,"output":12,"cache_read":0.5,"cache_write":null},"org":"qwen","subscription":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"aion-labs/aion-3.5-mini","name":"AionLabs: Aion 3.5 Mini","provider":"aionlabs","provider_display":"AionLabs","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7,"output":1.4,"cache_read":0.18,"cache_write":null},"org":"aion-labs","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"aion-labs/aion-3.5","name":"AionLabs: Aion 3.5","provider":"aionlabs","provider_display":"AionLabs","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":6,"cache_read":0.75,"cache_write":null},"org":"aion-labs","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"upstage/solar-mini4","name":"Upstage: Solar Mini 4","provider":"upstage","provider_display":"Upstage","quantization":"unknown","discount":0.5,"context_length":524288,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","frequency_penalty","presence_penalty","parallel_tool_calls","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.049999999999999996,"output":0.19999999999999998,"cache_read":0.005,"cache_write":null},"org":"upstage","zdr":true,"modelsdev":{"base_url":"https://api.upstage.ai/v1/solar","model_id":"solar-mini4","doc_url":"https://developers.upstage.ai/docs/apis/chat","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-02","description":"Upstage's compact, cost-efficient model for agentic use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.1,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1155,"win_rate":33.2,"rank":93}}},{"id":"cohere/command-a-plus","name":"Cohere: Command A+","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":192000,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":128000,"uptime_1d":100,"pricing":{"input":0.3,"output":1.5,"cache_read":0.15,"cache_write":null},"org":"cohere","zdr":true,"modelsdev":{"base_url":null,"model_id":"command-a-plus-05-2026","doc_url":"https://docs.cohere.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-05-20","knowledge_cutoff":"2025-04-01","description":"Cohere's stronger command model for multilingual agents and enterprise workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.2,"coding_index":27.8,"agentic_index":1,"design_arena_best":null}},{"id":"openai/gpt-6-luna-pro:flex","name":"OpenAI: GPT-6 Luna Pro (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":79.67145790554414,"pricing":{"input":0.049999999999999996,"output":0.25,"cache_read":0.005,"cache_write":0.0625},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-luna-pro","name":"OpenAI: GPT-6 Luna Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.01,"cache_write":0.125},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-luna-pro","name":"OpenAI: GPT-6 Luna Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.01,"cache_write":0.125},"org":"openai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-luna-pro:fast","name":"OpenAI: GPT-6 Luna Pro (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1,"cache_read":0.02,"cache_write":0.25},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-luna-pro:batch","name":"OpenAI: GPT-6 Luna Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.049999999999999996,"output":0.25,"cache_read":0.005,"cache_write":0.0625},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-luna:flex","name":"OpenAI: GPT-6 Luna (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":74.93055555555556,"pricing":{"input":0.049999999999999996,"output":0.25,"cache_read":0.005,"cache_write":0.0625},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6-luna","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-05-18","description":"OpenAI's most efficient model for focused, high-volume tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.8,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1442.8129943072395,"arena_text_rank":91,"arena_text_rating_lower":1438.1883147148455,"arena_text_rating_upper":1447.4376738996334,"arena_text_vote_count":49617,"arena_text_date":"2026-10-15","arena_creative_writing":1410.0344781879853,"arena_creative_writing_rank":91,"arena_creative_writing_rating_lower":1402.9014608939249,"arena_creative_writing_rating_upper":1417.1674954820458,"arena_creative_writing_vote_count":11078,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-luna","name":"OpenAI: GPT-6 Luna","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.01,"cache_write":0.125},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25},{"above_tokens":272000,"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}],"modelsdev":{"base_url":null,"model_id":"gpt-6-luna","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-05-18","description":"OpenAI's most efficient model for focused, high-volume tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.8,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1442.8129943072395,"arena_text_rank":91,"arena_text_rating_lower":1438.1883147148455,"arena_text_rating_upper":1447.4376738996334,"arena_text_vote_count":49617,"arena_text_date":"2026-10-15","arena_creative_writing":1410.0344781879853,"arena_creative_writing_rank":91,"arena_creative_writing_rating_lower":1402.9014608939249,"arena_creative_writing_rating_upper":1417.1674954820458,"arena_creative_writing_vote_count":11078,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-luna","name":"OpenAI: GPT-6 Luna","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.01,"cache_write":0.125},"org":"openai","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25},{"above_tokens":272000,"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}],"modelsdev":{"base_url":null,"model_id":"gpt-6-luna","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-05-18","description":"OpenAI's most efficient model for focused, high-volume tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.8,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1442.8129943072395,"arena_text_rank":91,"arena_text_rating_lower":1438.1883147148455,"arena_text_rating_upper":1447.4376738996334,"arena_text_vote_count":49617,"arena_text_date":"2026-10-15","arena_creative_writing":1410.0344781879853,"arena_creative_writing_rank":91,"arena_creative_writing_rating_lower":1402.9014608939249,"arena_creative_writing_rating_upper":1417.1674954820458,"arena_creative_writing_vote_count":11078,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-luna","name":"OpenAI: GPT-6 Luna","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375},"org":"openai","modelsdev":{"base_url":null,"model_id":"openai.gpt-6-luna","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-05-18","description":"OpenAI's most efficient model for focused, high-volume tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.8,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1442.8129943072395,"arena_text_rank":91,"arena_text_rating_lower":1438.1883147148455,"arena_text_rating_upper":1447.4376738996334,"arena_text_vote_count":49617,"arena_text_date":"2026-10-15","arena_creative_writing":1410.0344781879853,"arena_creative_writing_rank":91,"arena_creative_writing_rating_lower":1402.9014608939249,"arena_creative_writing_rating_upper":1417.1674954820458,"arena_creative_writing_vote_count":11078,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-luna:fast","name":"OpenAI: GPT-6 Luna (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1,"cache_read":0.02,"cache_write":0.25},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6-luna","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-05-18","description":"OpenAI's most efficient model for focused, high-volume tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.8,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1442.8129943072395,"arena_text_rank":91,"arena_text_rating_lower":1438.1883147148455,"arena_text_rating_upper":1447.4376738996334,"arena_text_vote_count":49617,"arena_text_date":"2026-10-15","arena_creative_writing":1410.0344781879853,"arena_creative_writing_rank":91,"arena_creative_writing_rating_lower":1402.9014608939249,"arena_creative_writing_rating_upper":1417.1674954820458,"arena_creative_writing_vote_count":11078,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-luna:batch","name":"OpenAI: GPT-6 Luna (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":0.049999999999999996,"output":0.25,"cache_read":0.005,"cache_write":0.0625},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6-luna","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-05-18","description":"OpenAI's most efficient model for focused, high-volume tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.8,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1442.8129943072395,"arena_text_rank":91,"arena_text_rating_lower":1438.1883147148455,"arena_text_rating_upper":1447.4376738996334,"arena_text_vote_count":49617,"arena_text_date":"2026-10-15","arena_creative_writing":1410.0344781879853,"arena_creative_writing_rank":91,"arena_creative_writing_rating_lower":1402.9014608939249,"arena_creative_writing_rating_upper":1417.1674954820458,"arena_creative_writing_vote_count":11078,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-sol-pro:flex","name":"OpenAI: GPT-6 Sol Pro (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-sol-pro","name":"OpenAI: GPT-6 Sol Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-sol-pro","name":"OpenAI: GPT-6 Sol Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","verbosity","response_format","seed","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-sol-pro:fast","name":"OpenAI: GPT-6 Sol Pro (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":4,"output":20,"cache_read":0.39999999999999997,"cache_write":5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-sol-pro:batch","name":"OpenAI: GPT-6 Sol Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-sol:flex","name":"OpenAI: GPT-6 Sol (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-04-20","description":"OpenAI model for complex coding and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":47.6,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1459.0243436054134,"arena_text_rank":61,"arena_text_rating_lower":1452.6775146046048,"arena_text_rating_upper":1465.3711726062222,"arena_text_vote_count":12466,"arena_text_date":"2026-10-15","arena_creative_writing":1437.8631741285064,"arena_creative_writing_rank":61,"arena_creative_writing_rating_lower":1425.2067651679,"arena_creative_writing_rating_upper":1450.519583089113,"arena_creative_writing_vote_count":2587,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-sol","name":"OpenAI: GPT-6 Sol","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":4,"output":15,"cache_read":0.4,"cache_write":5},{"above_tokens":272000,"input":4,"output":15,"cache_read":0.4,"cache_write":5}],"modelsdev":{"base_url":null,"model_id":"gpt-6-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-04-20","description":"OpenAI model for complex coding and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":47.6,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1459.0243436054134,"arena_text_rank":61,"arena_text_rating_lower":1452.6775146046048,"arena_text_rating_upper":1465.3711726062222,"arena_text_vote_count":12466,"arena_text_date":"2026-10-15","arena_creative_writing":1437.8631741285064,"arena_creative_writing_rank":61,"arena_creative_writing_rating_lower":1425.2067651679,"arena_creative_writing_rating_upper":1450.519583089113,"arena_creative_writing_vote_count":2587,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-sol","name":"OpenAI: GPT-6 Sol","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":4,"output":15,"cache_read":0.4,"cache_write":5},{"above_tokens":272000,"input":4,"output":15,"cache_read":0.4,"cache_write":5}],"modelsdev":{"base_url":null,"model_id":"gpt-6-sol","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-04-20","description":"OpenAI model for complex coding and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":47.6,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1459.0243436054134,"arena_text_rank":61,"arena_text_rating_lower":1452.6775146046048,"arena_text_rating_upper":1465.3711726062222,"arena_text_vote_count":12466,"arena_text_date":"2026-10-15","arena_creative_writing":1437.8631741285064,"arena_creative_writing_rank":61,"arena_creative_writing_rating_lower":1425.2067651679,"arena_creative_writing_rating_upper":1450.519583089113,"arena_creative_writing_vote_count":2587,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-sol","name":"OpenAI: GPT-6 Sol","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75},"org":"openai","modelsdev":{"base_url":null,"model_id":"global.openai.gpt-6-sol","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-04-20","description":"OpenAI model for complex coding and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":47.6,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1459.0243436054134,"arena_text_rank":61,"arena_text_rating_lower":1452.6775146046048,"arena_text_rating_upper":1465.3711726062222,"arena_text_vote_count":12466,"arena_text_date":"2026-10-15","arena_creative_writing":1437.8631741285064,"arena_creative_writing_rank":61,"arena_creative_writing_rating_lower":1425.2067651679,"arena_creative_writing_rating_upper":1450.519583089113,"arena_creative_writing_vote_count":2587,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-sol:fast","name":"OpenAI: GPT-6 Sol (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":99.76580796252928,"pricing":{"input":4,"output":20,"cache_read":0.39999999999999997,"cache_write":5},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-04-20","description":"OpenAI model for complex coding and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":47.6,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1459.0243436054134,"arena_text_rank":61,"arena_text_rating_lower":1452.6775146046048,"arena_text_rating_upper":1465.3711726062222,"arena_text_vote_count":12466,"arena_text_date":"2026-10-15","arena_creative_writing":1437.8631741285064,"arena_creative_writing_rank":61,"arena_creative_writing_rating_lower":1425.2067651679,"arena_creative_writing_rating_upper":1450.519583089113,"arena_creative_writing_vote_count":2587,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-sol:batch","name":"OpenAI: GPT-6 Sol (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-04-20","description":"OpenAI model for complex coding and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":47.6,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1459.0243436054134,"arena_text_rank":61,"arena_text_rating_lower":1452.6775146046048,"arena_text_rating_upper":1465.3711726062222,"arena_text_vote_count":12466,"arena_text_date":"2026-10-15","arena_creative_writing":1437.8631741285064,"arena_creative_writing_rank":61,"arena_creative_writing_rating_lower":1425.2067651679,"arena_creative_writing_rating_upper":1450.519583089113,"arena_creative_writing_vote_count":2587,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":4,"output":20,"cache_read":0.19999999999999998,"cache_write":5},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":58.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1466,"win_rate":64.9,"rank":1},"arena_text":1508.1664796431178,"arena_text_rank":3,"arena_text_rating_lower":1500.8355453341774,"arena_text_rating_upper":1515.497413952058,"arena_text_vote_count":8300,"arena_text_date":"2026-10-15","arena_creative_writing":1519.076672822608,"arena_creative_writing_rank":1,"arena_creative_writing_rating_lower":1504.0445020400361,"arena_creative_writing_rating_upper":1534.10884360518,"arena_creative_writing_vote_count":1945,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.89293361884368,"pricing":{"input":4,"output":20,"cache_read":0.19999999999999998,"cache_write":5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":58.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1466,"win_rate":64.9,"rank":1},"arena_text":1508.1664796431178,"arena_text_rank":3,"arena_text_rating_lower":1500.8355453341774,"arena_text_rating_upper":1515.497413952058,"arena_text_vote_count":8300,"arena_text_date":"2026-10-15","arena_creative_writing":1519.076672822608,"arena_creative_writing_rank":1,"arena_creative_writing_rating_lower":1504.0445020400361,"arena_creative_writing_rating_upper":1534.10884360518,"arena_creative_writing_vote_count":1945,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","response_format","tool_choice","tools","verbosity","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":4,"output":20,"cache_read":0.19999999999999998,"cache_write":5},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":58.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1466,"win_rate":64.9,"rank":1},"arena_text":1508.1664796431178,"arena_text_rank":3,"arena_text_rating_lower":1500.8355453341774,"arena_text_rating_upper":1515.497413952058,"arena_text_vote_count":8300,"arena_text_date":"2026-10-15","arena_creative_writing":1519.076672822608,"arena_creative_writing_rank":1,"arena_creative_writing_rating_lower":1504.0445020400361,"arena_creative_writing_rating_upper":1534.10884360518,"arena_creative_writing_vote_count":1945,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":4,"output":20,"cache_read":0.19999999999999998,"cache_write":5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":58.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1466,"win_rate":64.9,"rank":1},"arena_text":1508.1664796431178,"arena_text_rank":3,"arena_text_rating_lower":1500.8355453341774,"arena_text_rating_upper":1515.497413952058,"arena_text_vote_count":8300,"arena_text_date":"2026-10-15","arena_creative_writing":1519.076672822608,"arena_creative_writing_rank":1,"arena_creative_writing_rating_lower":1504.0445020400361,"arena_creative_writing_rating_upper":1534.10884360518,"arena_creative_writing_vote_count":1945,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":4,"output":20,"cache_read":0.19999999999999998,"cache_write":5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":58.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1466,"win_rate":64.9,"rank":1},"arena_text":1508.1664796431178,"arena_text_rank":3,"arena_text_rating_lower":1500.8355453341774,"arena_text_rating_upper":1515.497413952058,"arena_text_vote_count":8300,"arena_text_date":"2026-10-15","arena_creative_writing":1519.076672822608,"arena_creative_writing_rank":1,"arena_creative_writing_rating_lower":1504.0445020400361,"arena_creative_writing_rating_upper":1534.10884360518,"arena_creative_writing_vote_count":1945,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-5.5:fast","name":"Anthropic: Claude Opus 5.5 (fast)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":8,"output":40,"cache_read":0.39999999999999997,"cache_write":10},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":58.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1466,"win_rate":64.9,"rank":1},"arena_text":1508.1664796431178,"arena_text_rank":3,"arena_text_rating_lower":1500.8355453341774,"arena_text_rating_upper":1515.497413952058,"arena_text_vote_count":8300,"arena_text_date":"2026-10-15","arena_creative_writing":1519.076672822608,"arena_creative_writing_rank":1,"arena_creative_writing_rating_lower":1504.0445020400361,"arena_creative_writing_rating_upper":1534.10884360518,"arena_creative_writing_vote_count":1945,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-5.5:batch","name":"Anthropic: Claude Opus 5.5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":2,"output":10,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":58.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1466,"win_rate":64.9,"rank":1},"arena_text":1508.1664796431178,"arena_text_rank":3,"arena_text_rating_lower":1500.8355453341774,"arena_text_rating_upper":1515.497413952058,"arena_text_vote_count":8300,"arena_text_date":"2026-10-15","arena_creative_writing":1519.076672822608,"arena_creative_writing_rank":1,"arena_creative_writing_rating_lower":1504.0445020400361,"arena_creative_writing_rating_upper":1534.10884360518,"arena_creative_writing_vote_count":1945,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-pro-ultraspeed","name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","provider":"xiaomi","provider_display":"Xiaomi","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","response_format","tools","tool_choice","frequency_penalty","presence_penalty","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":4.35,"output":8.7,"cache_read":0.036,"cache_write":null},"org":"xiaomi","subscription":true,"modelsdev":{"base_url":"https://api.xiaomimimo.com/v1","model_id":"mimo-v2.6-pro-ultraspeed","doc_url":"https://platform.xiaomimimo.com/#/docs","confidence":"high","source":"models.dev","release_date":"2026-09-21","knowledge_cutoff":null,"description":"MiMo pro model for strong multimodal reasoning and agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","provider":"io-net","provider_display":"Io Net","quantization":"fp8","discount":0,"context_length":1048320,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","seed","stop","top_k","top_p","presence_penalty","frequency_penalty","repetition_penalty","tools","tool_choice","logprobs","top_logprobs","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.01685393258427,"pricing":{"input":0.09999999999999999,"output":0.28,"cache_read":0.003,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","provider":"darkbloom","provider_display":"Darkbloom","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.58454106280193,"pricing":{"input":0.09999999999999999,"output":0.28,"cache_read":0.049999999999999996,"cache_write":null},"org":"xiaomi","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","provider":"gmicloud","provider_display":"GMICloud","quantization":"bf16","discount":0.15,"context_length":1050000,"max_completion_tokens":945000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":95.43808834178131,"pricing":{"input":0.119,"output":0.238,"cache_read":0.00255,"cache_write":null},"org":"xiaomi","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","provider":"makora","provider_display":"Makora","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.13,"output":0.28,"cache_read":0.002,"cache_write":null},"org":"xiaomi","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","provider":"relace","provider_display":"Relace","quantization":"mxfp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.13,"output":0.28,"cache_read":0.003,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice","parallel_tool_calls","logprobs","top_logprobs","repetition_penalty"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.14,"output":0.28,"cache_read":0.003,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.7878787878788,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"xiaomimimo/mimo-v2.6-flash","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","provider":"xiaomi","provider_display":"Xiaomi","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","response_format","tools","tool_choice","frequency_penalty","presence_penalty","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":null},"org":"xiaomi","subscription":true,"modelsdev":{"base_url":"https://api.xiaomimimo.com/v1","model_id":"mimo-v2.6-flash","doc_url":"https://platform.xiaomimimo.com/#/docs","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.18614718614718,"pricing":{"input":0.175,"output":0.35,"cache_read":0.00375,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-pro","name":"Xiaomi: MiMo-V2.6-Pro","provider":"gmicloud","provider_display":"GMICloud","quantization":"bf16","discount":0.15,"context_length":1050000,"max_completion_tokens":945000,"uptime_30m":96.66666666666667,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":85.83333333333333,"pricing":{"input":0.36974999999999997,"output":0.7394999999999999,"cache_read":0.0034,"cache_write":null},"org":"xiaomi","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1335,"win_rate":58.4,"rank":7},"arena_text":1479.194755229377,"arena_text_rank":27,"arena_text_rating_lower":1469.827446672319,"arena_text_rating_upper":1488.5620637864351,"arena_text_vote_count":4075,"arena_text_date":"2026-10-15","arena_creative_writing":1444.679173566022,"arena_creative_writing_rank":52,"arena_creative_writing_rating_lower":1423.5979241643079,"arena_creative_writing_rating_upper":1465.760422967736,"arena_creative_writing_vote_count":793,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-pro","name":"Xiaomi: MiMo-V2.6-Pro","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"xiaomimimo/mimo-v2.6-pro","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":null,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1335,"win_rate":58.4,"rank":7},"arena_text":1479.194755229377,"arena_text_rank":27,"arena_text_rating_lower":1469.827446672319,"arena_text_rating_upper":1488.5620637864351,"arena_text_vote_count":4075,"arena_text_date":"2026-10-15","arena_creative_writing":1444.679173566022,"arena_creative_writing_rank":52,"arena_creative_writing_rating_lower":1423.5979241643079,"arena_creative_writing_rating_upper":1465.760422967736,"arena_creative_writing_vote_count":793,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-pro","name":"Xiaomi: MiMo-V2.6-Pro","provider":"xiaomi","provider_display":"Xiaomi","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","response_format","tools","tool_choice","frequency_penalty","presence_penalty","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":null},"org":"xiaomi","subscription":true,"modelsdev":{"base_url":"https://api.xiaomimimo.com/v1","model_id":"mimo-v2.6-pro","doc_url":"https://platform.xiaomimimo.com/#/docs","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Pro model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1335,"win_rate":58.4,"rank":7},"arena_text":1479.194755229377,"arena_text_rank":27,"arena_text_rating_lower":1469.827446672319,"arena_text_rating_upper":1488.5620637864351,"arena_text_vote_count":4075,"arena_text_date":"2026-10-15","arena_creative_writing":1444.679173566022,"arena_creative_writing_rank":52,"arena_creative_writing_rating_lower":1423.5979241643079,"arena_creative_writing_rating_upper":1465.760422967736,"arena_creative_writing_vote_count":793,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.6-pro","name":"Xiaomi: MiMo-V2.6-Pro","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":-0.2,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":90,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":94.2982456140351,"pricing":{"input":0.522,"output":1.044,"cache_read":0.00432,"cache_write":null},"org":"xiaomi","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-22","knowledge_cutoff":null,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1335,"win_rate":58.4,"rank":7},"arena_text":1479.194755229377,"arena_text_rank":27,"arena_text_rating_lower":1469.827446672319,"arena_text_rating_upper":1488.5620637864351,"arena_text_vote_count":4075,"arena_text_date":"2026-10-15","arena_creative_writing":1444.679173566022,"arena_creative_writing_rank":52,"arena_creative_writing_rating_lower":1423.5979241643079,"arena_creative_writing_rating_upper":1465.760422967736,"arena_creative_writing_vote_count":793,"arena_creative_writing_date":"2026-10-15"}},{"id":"x-ai/grok-4.7","name":"SpaceXAI: Grok 4.7","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":500000,"max_completion_tokens":450000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":6,"cache_read":0.5,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"context_price_tiers":[{"above_tokens":200000,"input":4,"output":12,"cache_read":1,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"grok-4.7","doc_url":"https://docs.x.ai/docs/models","confidence":"high","source":"models.dev","release_date":"2026-09-21","knowledge_cutoff":"2026-05","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":35,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":52.7,"rank":15},"arena_text":1443.9789336394695,"arena_text_rank":89,"arena_text_rating_lower":1437.5593577926459,"arena_text_rating_upper":1450.3985094862933,"arena_text_vote_count":11591,"arena_text_date":"2026-10-15","arena_creative_writing":1423.757121376712,"arena_creative_writing_rank":78,"arena_creative_writing_rating_lower":1411.1481840860185,"arena_creative_writing_rating_upper":1436.3660586674052,"arena_creative_writing_vote_count":2589,"arena_creative_writing_date":"2026-10-15"}},{"id":"x-ai/grok-4.7:priority","name":"SpaceXAI: Grok 4.7 (priority)","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":500000,"max_completion_tokens":450000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":4,"output":12,"cache_read":1,"cache_write":null},"org":"xai","subscription":true,"modelsdev":{"base_url":null,"model_id":"grok-4.7","doc_url":"https://docs.x.ai/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-21","knowledge_cutoff":"2026-05","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":35,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":52.7,"rank":15},"arena_text":1443.9789336394695,"arena_text_rank":89,"arena_text_rating_lower":1437.5593577926459,"arena_text_rating_upper":1450.3985094862933,"arena_text_vote_count":11591,"arena_text_date":"2026-10-15","arena_creative_writing":1423.757121376712,"arena_creative_writing_rank":78,"arena_creative_writing_rating_lower":1411.1481840860185,"arena_creative_writing_rating_upper":1436.3660586674052,"arena_creative_writing_vote_count":2589,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-omni-flash","name":"Qwen: Qwen3.8 Omni Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","structured_outputs","top_k","frequency_penalty","stop","logprobs","top_logprobs","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":983616,"uptime_1d":100,"pricing":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.8-omni-flash","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-09-17","knowledge_cutoff":null,"description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"prism-ml/ternary-bonsai-2-27b","name":"PrismML: Ternary Bonsai 2 27B","provider":"darkbloom","provider_display":"Darkbloom","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.075,"output":0.5,"cache_read":0.0375,"cache_write":null},"org":"prism-ml","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"z-ai/glm-5.3-flashx","name":"Z.ai: GLM 5.3 FlashX","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.37,"output":1.25,"cache_read":0.09,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5.3-flashx","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-09-18","knowledge_cutoff":null,"description":"High-speed GLM-5.3-Flash serving option for coding and agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"inference-net/schematron-v2-turbo","name":"Inference.net: Schematron V2 Turbo","provider":"inferencenet","provider_display":"InferenceNet","quantization":"bf16","discount":0,"context_length":128000,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","logit_bias","response_format","structured_outputs","repetition_penalty"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.49238578680203,"pricing":{"input":0.03,"output":0.15,"cache_read":0.03,"cache_write":null},"org":"inference-net","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"inference-net/schematron-v2-small","name":"Inference.net: Schematron V2 Small","provider":"inferencenet","provider_display":"InferenceNet","quantization":"bf16","discount":0,"context_length":128000,"max_completion_tokens":4096,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","logit_bias","response_format","structured_outputs","repetition_penalty"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.049999999999999996,"output":0.22999999999999998,"cache_read":0.049999999999999996,"cache_write":null},"org":"inference-net","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"sakana/fugu-ultra-v2","name":"Sakana: Fugu Ultra v2","provider":"sakana","provider_display":"Sakana AI","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","structured_outputs","web_search_options","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"sakana","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"sakana/fugu-max","name":"Sakana: Fugu Max","provider":"sakana","provider_display":"Sakana AI","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","structured_outputs","web_search_options","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":6,"cache_read":0.25,"cache_write":null},"org":"sakana","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"openinference","provider_display":"OpenInference","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","stop","seed","top_p","frequency_penalty","presence_penalty","top_k","min_p","logit_bias","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.0298,"output":1.37,"cache_read":0.027299999999999998,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"morph","provider_display":"Morph","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.79166666666667,"pricing":{"input":0.044,"output":0.38299999999999995,"cache_read":0.004,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.851,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.044700000000000004,"output":0.17880000000000001,"cache_read":0.000894,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"relace","provider_display":"Relace","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","stop","max_tokens","logit_bias","frequency_penalty","presence_penalty","repetition_penalty","tools","tool_choice","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.07,"output":0.5,"cache_read":0.008,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"decart","provider_display":"Decart","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09,"output":0.18,"cache_read":0.018,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"sail-research","provider_display":"Sail Research","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","presence_penalty","seed","stop","temperature","top_k","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09,"output":0.25,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"inferencenet","provider_display":"InferenceNet","quantization":"fp8","discount":0,"context_length":1040000,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.103,"output":0.6,"cache_read":0.008,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"reka","provider_display":"Reka","quantization":"unknown","discount":0.3,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","temperature","top_p","top_k","max_tokens","stop","seed","frequency_penalty","presence_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.88888888888889,"pricing":{"input":0.105,"output":0.84,"cache_read":0.007,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash:flex","name":"DeepSeek: DeepSeek V4.1 Flash (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0.3,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":96.47779479326188,"pricing":{"input":0.112,"output":0.33599999999999997,"cache_read":0.00336,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4.1-Flash","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.13,"output":0.65,"cache_read":0.002,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.40277777777777,"pricing":{"input":0.135,"output":0.54,"cache_read":0.0135,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.51,"context_length":1024000,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","logprobs","top_logprobs","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.14700000000000002,"output":0.5880000000000001,"cache_read":0.0029400000000000003,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.165,"output":0.66,"cache_read":0.016499999999999997,"cache_write":null},"org":"deepseek","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.4,"context_length":1048575,"max_completion_tokens":943717,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.18,"output":0.72,"cache_read":0.0036,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.35,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":false,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.195,"output":0.78,"cache_read":0.0039000000000000003,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-v4.1-flash","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","logprobs","top_logprobs","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash:priority","name":"DeepSeek: DeepSeek V4.1 Flash (priority)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0.3,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":0,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":25.17385257301808,"pricing":{"input":0.21,"output":0.63,"cache_read":0.0063,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4.1-Flash","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.21,"output":0.84,"cache_read":0.004200000000000001,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/deepseek-v4p1-flash","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0.3,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.21,"output":0.84,"cache_read":0.004200000000000001,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","logprobs","top_logprobs","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.22499999999999998,"output":0.8999999999999999,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"deepseek-v4.1-flash","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"makora","provider_display":"Makora","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.26,"output":1.17,"cache_read":0.0058,"cache_write":null},"org":"deepseek","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"crusoe","provider_display":"Crusoe","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.29,"output":1.2,"cache_read":0.007,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","tools","tool_choice","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":1048000,"max_completion_tokens":943200,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.86111111111111,"pricing":{"input":0.3,"output":1.2,"cache_read":0.01,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"deepseek-ai/DeepSeek-V4.1-Flash","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"primeintellect","provider_display":"PrimeIntellect","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p","response_format","structured_outputs","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice","parallel_tool_calls","logprobs","top_logprobs","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.3,"output":1.2,"cache_read":0.003,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"baseten","provider_display":"BaseTen","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":96.66666666666667,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.92559523809523,"pricing":{"input":0.3,"output":1.2,"cache_read":0.007,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"deepseek-ai/DeepSeek-V4.1-Flash","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4.1-Flash","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"modal","provider_display":"Modal","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","stop","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.us-west.modal.direct/v1","model_id":"deepseek-ai/DeepSeek-V4.1-Flash","doc_url":"https://modal.com/docs/guide/endpoints","confidence":"high","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":96.66666666666667,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.3,"output":1.2,"cache_read":0.0075,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash:fast","name":"DeepSeek: DeepSeek V4.1 Flash (fast)","provider":"baseten","provider_display":"BaseTen","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":20.689655172413794,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","reasoning_effort"],"supports_tool_choice":false,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":19.20849420849421,"pricing":{"input":0.6,"output":2.4,"cache_read":0.014,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"deepseek-ai/DeepSeek-V4.1-Flash","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"medium","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash:batch","name":"DeepSeek: DeepSeek V4.1 Flash (batch)","provider":"sail-research","provider_display":"Sail Research","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","presence_penalty","seed","stop","temperature","top_k","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.049999999999999996,"output":0.15,"cache_read":0.004,"cache_write":null},"org":"deepseek","open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4.1-flash:batch","name":"DeepSeek: DeepSeek V4.1 Flash (batch)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0.3,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","structured_outputs","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.112,"output":0.33599999999999997,"cache_read":0.00336,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4.1-Flash","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"inception/mercury-2.5","name":"Inception: Mercury 2.5","provider":"inception","provider_display":"Inception","quantization":"unknown","discount":0.8,"context_length":260000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","temperature","tools","tool_choice","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.04,"output":0.15,"cache_read":0.004,"cache_write":null},"org":"inception","zdr":true,"modelsdev":{"base_url":"https://api.inceptionlabs.ai/v1/","model_id":"mercury-2.5","doc_url":"https://docs.inceptionlabs.ai/get-started/models","confidence":"high","source":"models.dev","release_date":"2026-09-08","knowledge_cutoff":"2025-11-01","description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.3,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"nex-agi/nex-n2.5-mini","name":"Nex AGI: Nex-N2.5-Mini","provider":"nex-agi","provider_display":"Nex AGI","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_k","top_p","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.23611111111111,"pricing":{"input":0.024999999999999998,"output":0.09999999999999999,"cache_read":0.0025,"cache_write":null},"org":"nex-agi","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"nex-agi/nex-n2.5-pro","name":"Nex AGI: Nex-N2.5-Pro","provider":"nex-agi","provider_display":"Nex AGI","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_k","top_p","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.89615784008308,"pricing":{"input":0.075,"output":0.25,"cache_read":0.015,"cache_write":null},"org":"nex-agi","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-astra:flex","name":"OpenAI: GPT-6 Astra (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6-astra","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-04","knowledge_cutoff":"2026-04-30","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":56.9,"coding_index":76.9,"agentic_index":51,"design_arena_best":null,"arena_text":1477.319231586918,"arena_text_rank":30,"arena_text_rating_lower":1471.0194563904267,"arena_text_rating_upper":1483.6190067834093,"arena_text_vote_count":12163,"arena_text_date":"2026-10-15","arena_creative_writing":1449.932706761758,"arena_creative_writing_rank":38,"arena_creative_writing_rating_lower":1437.6886399434397,"arena_creative_writing_rating_upper":1462.1767735800763,"arena_creative_writing_vote_count":2718,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-astra","name":"OpenAI: GPT-6 Astra","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":99.58333333333333,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"openai","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":20,"output":75,"cache_read":2,"cache_write":25},{"above_tokens":272000,"input":20,"output":75,"cache_read":2,"cache_write":25}],"modelsdev":{"base_url":null,"model_id":"gpt-6-astra","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-09-04","knowledge_cutoff":"2026-04-30","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":56.9,"coding_index":76.9,"agentic_index":51,"design_arena_best":null,"arena_text":1477.319231586918,"arena_text_rank":30,"arena_text_rating_lower":1471.0194563904267,"arena_text_rating_upper":1483.6190067834093,"arena_text_vote_count":12163,"arena_text_date":"2026-10-15","arena_creative_writing":1449.932706761758,"arena_creative_writing_rank":38,"arena_creative_writing_rating_lower":1437.6886399434397,"arena_creative_writing_rating_upper":1462.1767735800763,"arena_creative_writing_vote_count":2718,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-astra","name":"OpenAI: GPT-6 Astra","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":92.01388888888889,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":20,"output":75,"cache_read":2,"cache_write":25},{"above_tokens":272000,"input":20,"output":75,"cache_read":2,"cache_write":25}],"modelsdev":{"base_url":null,"model_id":"gpt-6-astra","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-09-04","knowledge_cutoff":"2026-04-30","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":56.9,"coding_index":76.9,"agentic_index":51,"design_arena_best":null,"arena_text":1477.319231586918,"arena_text_rank":30,"arena_text_rating_lower":1471.0194563904267,"arena_text_rating_upper":1483.6190067834093,"arena_text_vote_count":12163,"arena_text_date":"2026-10-15","arena_creative_writing":1449.932706761758,"arena_creative_writing_rank":38,"arena_creative_writing_rating_lower":1437.6886399434397,"arena_creative_writing_rating_upper":1462.1767735800763,"arena_creative_writing_vote_count":2718,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-astra","name":"OpenAI: GPT-6 Astra","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":11,"output":55,"cache_read":1.1,"cache_write":13.75},"org":"openai","modelsdev":{"base_url":null,"model_id":"openai.gpt-6-astra","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-09-04","knowledge_cutoff":"2026-04-30","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":56.9,"coding_index":76.9,"agentic_index":51,"design_arena_best":null,"arena_text":1477.319231586918,"arena_text_rank":30,"arena_text_rating_lower":1471.0194563904267,"arena_text_rating_upper":1483.6190067834093,"arena_text_vote_count":12163,"arena_text_date":"2026-10-15","arena_creative_writing":1449.932706761758,"arena_creative_writing_rank":38,"arena_creative_writing_rating_lower":1437.6886399434397,"arena_creative_writing_rating_upper":1462.1767735800763,"arena_creative_writing_vote_count":2718,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-astra:fast","name":"OpenAI: GPT-6 Astra (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":20,"output":100,"cache_read":2,"cache_write":25},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6-astra","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-04","knowledge_cutoff":"2026-04-30","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":56.9,"coding_index":76.9,"agentic_index":51,"design_arena_best":null,"arena_text":1477.319231586918,"arena_text_rank":30,"arena_text_rating_lower":1471.0194563904267,"arena_text_rating_upper":1483.6190067834093,"arena_text_vote_count":12163,"arena_text_date":"2026-10-15","arena_creative_writing":1449.932706761758,"arena_creative_writing_rank":38,"arena_creative_writing_rating_lower":1437.6886399434397,"arena_creative_writing_rating_upper":1462.1767735800763,"arena_creative_writing_vote_count":2718,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-astra:ultrafast","name":"OpenAI: GPT-6 Astra (ultrafast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":60,"output":300,"cache_read":6,"cache_write":75},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6-astra","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-04","knowledge_cutoff":"2026-04-30","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":56.9,"coding_index":76.9,"agentic_index":51,"design_arena_best":null,"arena_text":1477.319231586918,"arena_text_rank":30,"arena_text_rating_lower":1471.0194563904267,"arena_text_rating_upper":1483.6190067834093,"arena_text_vote_count":12163,"arena_text_date":"2026-10-15","arena_creative_writing":1449.932706761758,"arena_creative_writing_rank":38,"arena_creative_writing_rating_lower":1437.6886399434397,"arena_creative_writing_rating_upper":1462.1767735800763,"arena_creative_writing_vote_count":2718,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-astra:batch","name":"OpenAI: GPT-6 Astra (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-6-astra","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-04","knowledge_cutoff":"2026-04-30","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":56.9,"coding_index":76.9,"agentic_index":51,"design_arena_best":null,"arena_text":1477.319231586918,"arena_text_rank":30,"arena_text_rating_lower":1471.0194563904267,"arena_text_rating_upper":1483.6190067834093,"arena_text_vote_count":12163,"arena_text_date":"2026-10-15","arena_creative_writing":1449.932706761758,"arena_creative_writing_rank":38,"arena_creative_writing_rating_lower":1437.6886399434397,"arena_creative_writing_rating_upper":1462.1767735800763,"arena_creative_writing_vote_count":2718,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-6-astra-pro:flex","name":"OpenAI: GPT-6 Astra Pro (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-astra-pro","name":"OpenAI: GPT-6 Astra Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":98.44357976653697,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"openai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-astra-pro","name":"OpenAI: GPT-6 Astra Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-astra-pro:fast","name":"OpenAI: GPT-6 Astra Pro (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":20,"output":100,"cache_read":2,"cache_write":25},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-astra-pro:ultrafast","name":"OpenAI: GPT-6 Astra Pro (ultrafast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":60,"output":300,"cache_read":6,"cache_write":75},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-6-astra-pro:batch","name":"OpenAI: GPT-6 Astra Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3.8-max-0902","name":"Qwen: Qwen3.8 Max (0902)","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":983616,"uptime_1d":99.23611111111111,"pricing":{"input":2,"output":6,"cache_read":0.25,"cache_write":null},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-10-20","knowledge_cutoff":null,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://llm.chutes.ai/v1/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":33.6,"coding_index":76.2,"agentic_index":56,"design_arena_best":null}},{"id":"meta/muse-spark-1.3-contributor","name":"Meta: Muse Spark 1.3 Contributor","provider":"meta","provider_display":"Meta","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.09999999999999999,"output":0.19999999999999998,"cache_read":0.002,"cache_write":null},"org":"meta","modelsdev":{"base_url":"https://api.meta.ai/v1","model_id":"muse-spark-1.3-contributor","doc_url":"https://dev.meta.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-09-02","knowledge_cutoff":null,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"meta/muse-spark-1.3","name":"Meta: Muse Spark 1.3","provider":"meta","provider_display":"Meta","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":null},"org":"meta","modelsdev":{"base_url":"https://api.meta.ai/v1","model_id":"muse-spark-1.3","doc_url":"https://dev.meta.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-09-02","knowledge_cutoff":null,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36.4,"coding_index":75.8,"agentic_index":55.5,"design_arena_best":{"category":"3d","elo":1393,"win_rate":63.5,"rank":6},"arena_text":1494.412724849286,"arena_text_rank":10,"arena_text_rating_lower":1488.8158760267218,"arena_text_rating_upper":1500.0095736718504,"arena_text_vote_count":17561,"arena_text_date":"2026-10-15","arena_creative_writing":1461.1749127946157,"arena_creative_writing_rank":29,"arena_creative_writing_rating_lower":1450.6495796980869,"arena_creative_writing_rating_upper":1471.7002458911445,"arena_creative_writing_vote_count":3844,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.8-flash:flex","name":"Google: Gemini 3.8 Flash (flex)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.0208333333333333},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.8-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-02","knowledge_cutoff":null,"description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":30.5,"coding_index":76.3,"agentic_index":40.2,"design_arena_best":{"category":"uicomponent","elo":1314,"win_rate":53.8,"rank":14},"arena_text":1496.3802615912373,"arena_text_rank":9,"arena_text_rating_lower":1491.7511847575463,"arena_text_rating_upper":1501.0093384249283,"arena_text_vote_count":37454,"arena_text_date":"2026-10-15","arena_creative_writing":1486.9392865970776,"arena_creative_writing_rank":7,"arena_creative_writing_rating_lower":1478.996252485179,"arena_creative_writing_rating_upper":1494.882320708976,"arena_creative_writing_vote_count":8232,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.8-flash","name":"Google: Gemini 3.8 Flash","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.0416666666666667},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3.8-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-09-02","knowledge_cutoff":null,"description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":30.5,"coding_index":76.3,"agentic_index":40.2,"design_arena_best":{"category":"uicomponent","elo":1314,"win_rate":53.8,"rank":14},"arena_text":1496.3802615912373,"arena_text_rank":9,"arena_text_rating_lower":1491.7511847575463,"arena_text_rating_upper":1501.0093384249283,"arena_text_vote_count":37454,"arena_text_date":"2026-10-15","arena_creative_writing":1486.9392865970776,"arena_creative_writing_rank":7,"arena_creative_writing_rating_lower":1478.996252485179,"arena_creative_writing_rating_upper":1494.882320708976,"arena_creative_writing_vote_count":8232,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.8-flash:priority","name":"Google: Gemini 3.8 Flash (priority)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.35,"output":6.75,"cache_read":0.135,"cache_write":0.075},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.8-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-02","knowledge_cutoff":null,"description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":30.5,"coding_index":76.3,"agentic_index":40.2,"design_arena_best":{"category":"uicomponent","elo":1314,"win_rate":53.8,"rank":14},"arena_text":1496.3802615912373,"arena_text_rank":9,"arena_text_rating_lower":1491.7511847575463,"arena_text_rating_upper":1501.0093384249283,"arena_text_vote_count":37454,"arena_text_date":"2026-10-15","arena_creative_writing":1486.9392865970776,"arena_creative_writing_rank":7,"arena_creative_writing_rating_lower":1478.996252485179,"arena_creative_writing_rating_upper":1494.882320708976,"arena_creative_writing_vote_count":8232,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.8-flash:batch","name":"Google: Gemini 3.8 Flash (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.0416666666666667},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.8-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-09-02","knowledge_cutoff":null,"description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":30.5,"coding_index":76.3,"agentic_index":40.2,"design_arena_best":{"category":"uicomponent","elo":1314,"win_rate":53.8,"rank":14},"arena_text":1496.3802615912373,"arena_text_rank":9,"arena_text_rating_lower":1491.7511847575463,"arena_text_rating_upper":1501.0093384249283,"arena_text_vote_count":37454,"arena_text_date":"2026-10-15","arena_creative_writing":1486.9392865970776,"arena_creative_writing_rank":7,"arena_creative_writing_rating_lower":1478.996252485179,"arena_creative_writing_rating_upper":1494.882320708976,"arena_creative_writing_vote_count":8232,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-fable-5.1","name":"Anthropic: Claude Fable 5.1","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tool_choice","tools","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.7,"coding_index":80.7,"agentic_index":57.2,"design_arena_best":{"category":"spreadsheet","elo":1416,"win_rate":70.4,"rank":1},"arena_text":1502.2862278899863,"arena_text_rank":6,"arena_text_rating_lower":1496.239481927182,"arena_text_rating_upper":1508.3329738527907,"arena_text_vote_count":14590,"arena_text_date":"2026-10-15","arena_creative_writing":1484.729535554378,"arena_creative_writing_rank":9,"arena_creative_writing_rating_lower":1473.299210694477,"arena_creative_writing_rating_upper":1496.1598604142787,"arena_creative_writing_vote_count":3284,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-fable-5.1","name":"Anthropic: Claude Fable 5.1","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.7,"coding_index":80.7,"agentic_index":57.2,"design_arena_best":{"category":"spreadsheet","elo":1416,"win_rate":70.4,"rank":1},"arena_text":1502.2862278899863,"arena_text_rank":6,"arena_text_rating_lower":1496.239481927182,"arena_text_rating_upper":1508.3329738527907,"arena_text_vote_count":14590,"arena_text_date":"2026-10-15","arena_creative_writing":1484.729535554378,"arena_creative_writing_rank":9,"arena_creative_writing_rating_lower":1473.299210694477,"arena_creative_writing_rating_upper":1496.1598604142787,"arena_creative_writing_vote_count":3284,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-fable-5.1","name":"Anthropic: Claude Fable 5.1","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.7,"coding_index":80.7,"agentic_index":57.2,"design_arena_best":{"category":"spreadsheet","elo":1416,"win_rate":70.4,"rank":1},"arena_text":1502.2862278899863,"arena_text_rank":6,"arena_text_rating_lower":1496.239481927182,"arena_text_rating_upper":1508.3329738527907,"arena_text_vote_count":14590,"arena_text_date":"2026-10-15","arena_creative_writing":1484.729535554378,"arena_creative_writing_rank":9,"arena_creative_writing_rating_lower":1473.299210694477,"arena_creative_writing_rating_upper":1496.1598604142787,"arena_creative_writing_vote_count":3284,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-fable-5.1","name":"Anthropic: Claude Fable 5.1","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","response_format","tool_choice","tools","verbosity","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.7,"coding_index":80.7,"agentic_index":57.2,"design_arena_best":{"category":"spreadsheet","elo":1416,"win_rate":70.4,"rank":1},"arena_text":1502.2862278899863,"arena_text_rank":6,"arena_text_rating_lower":1496.239481927182,"arena_text_rating_upper":1508.3329738527907,"arena_text_vote_count":14590,"arena_text_date":"2026-10-15","arena_creative_writing":1484.729535554378,"arena_creative_writing_rank":9,"arena_creative_writing_rating_lower":1473.299210694477,"arena_creative_writing_rating_upper":1496.1598604142787,"arena_creative_writing_vote_count":3284,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-fable-5.1:batch","name":"Anthropic: Claude Fable 5.1 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":5,"output":25,"cache_read":0.125,"cache_write":6.25},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.7,"coding_index":80.7,"agentic_index":57.2,"design_arena_best":{"category":"spreadsheet","elo":1416,"win_rate":70.4,"rank":1},"arena_text":1502.2862278899863,"arena_text_rank":6,"arena_text_rating_lower":1496.239481927182,"arena_text_rating_upper":1508.3329738527907,"arena_text_vote_count":14590,"arena_text_date":"2026-10-15","arena_creative_writing":1484.729535554378,"arena_creative_writing_rank":9,"arena_creative_writing_rating_lower":1473.299210694477,"arena_creative_writing_rating_upper":1496.1598604142787,"arena_creative_writing_vote_count":3284,"arena_creative_writing_date":"2026-10-15"}},{"id":"ibm-granite/granite-4.2-8b","name":"IBM: Granite 4.2 8B","provider":"coreweave","provider_display":"CoreWeave","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.06,"output":0.15,"cache_read":0.015,"cache_write":null},"org":"ibm","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-25","knowledge_cutoff":null,"description":"Granite 4.2 8B is an instruct model capable of enhanced tool calling, instruction following, and chat capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.1,"coding_index":22.4,"agentic_index":1.3,"design_arena_best":null,"arena_text":1290.1761926441807,"arena_text_rank":290,"arena_text_rating_lower":1279.0036546892693,"arena_text_rating_upper":1301.3487305990918,"arena_text_vote_count":3254,"arena_text_date":"2026-10-15","arena_creative_writing":1200.7601919979436,"arena_creative_writing_rank":325,"arena_creative_writing_rating_lower":1173.755372152443,"arena_creative_writing_rating_upper":1227.765011843444,"arena_creative_writing_vote_count":628,"arena_creative_writing_date":"2026-10-15"}},{"id":"tencent/hy4-preview","name":"Tencent: Hy4 preview","provider":"tencent","provider_display":"Tencent","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","stop","max_completion_tokens","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7505999999999999,"output":2.2509,"cache_read":0.0378,"cache_write":null},"org":"tencent","zdr":true,"modelsdev":{"base_url":"https://tokenhub.tencentmaas.com/v1","model_id":"hy4-preview","doc_url":"https://cloud.tencent.com/document/product/1823/130050","confidence":"high","source":"models.dev","release_date":"2026-08-28","knowledge_cutoff":null,"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"tencent/hy4-preview","name":"Tencent: Hy4 preview","provider":"gmicloud","provider_display":"GMICloud","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":90.21739130434783,"pricing":{"input":0.834,"output":2.501,"cache_read":0.041999999999999996,"cache_write":null},"org":"tencent","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-28","knowledge_cutoff":null,"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.tencent.com/document/product/1823/130050","reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"tencent/hy4-preview","name":"Tencent: Hy4 preview","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.59049959049959,"pricing":{"input":0.834,"output":2.501,"cache_read":0.041999999999999996,"cache_write":null},"org":"tencent","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-28","knowledge_cutoff":null,"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.tencent.com/document/product/1823/130050","reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"tencent/hy4-preview","name":"Tencent: Hy4 preview","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice","parallel_tool_calls","logprobs","top_logprobs","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":83.75089477451682,"pricing":{"input":0.834,"output":2.501,"cache_read":0.041999999999999996,"cache_write":null},"org":"tencent","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-28","knowledge_cutoff":null,"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.tencent.com/document/product/1823/130050","reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"tencent/hy4-preview","name":"Tencent: Hy4 preview","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.834,"output":2.501,"cache_read":0.041999999999999996,"cache_write":null},"org":"tencent","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"tencent/hy4-preview","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-08-28","knowledge_cutoff":null,"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"tencent/hy4-preview","name":"Tencent: Hy4 preview","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.834,"output":2.501,"cache_read":0.041999999999999996,"cache_write":null},"org":"tencent","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-28","knowledge_cutoff":null,"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.tencent.com/document/product/1823/130050","reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3.8-flash","name":"Qwen: Qwen3.8 Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","structured_outputs","top_k","frequency_penalty","stop","logprobs","top_logprobs","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":983616,"uptime_1d":100,"pricing":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.8-flash","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"relace","provider_display":"Relace","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.051300000000000005,"output":0.0701,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"openinference","provider_display":"OpenInference","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","stop","seed","response_format","structured_outputs","top_p","frequency_penalty","presence_penalty","top_k","min_p","logit_bias","repetition_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.052899999999999996,"output":0.083,"cache_read":0.048100000000000004,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"darkbloom","provider_display":"Darkbloom","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.67256637168141,"pricing":{"input":0.065,"output":0.18,"cache_read":0.0325,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.5,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":96.66666666666667,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.95833333333334,"pricing":{"input":0.075,"output":0.25,"cache_read":0.015,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"sail-research","provider_display":"Sail Research","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","presence_penalty","seed","stop","temperature","top_k","top_p","structured_outputs","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.84732824427482,"pricing":{"input":0.07835,"output":0.25,"cache_read":0.026099999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"near-ai","provider_display":"Near AI","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","max_tokens","stop","seed","logit_bias","response_format","tools","tool_choice","logprobs","top_logprobs","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.08,"output":0.5,"cache_read":0.012,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.44,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.86111111111111,"pricing":{"input":0.08399999999999999,"output":0.28,"cache_read":0.016800000000000002,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-5.3-flash","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.41,"context_length":1024000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.375,"pricing":{"input":0.08850000000000001,"output":0.295,"cache_read":0.0177,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"inferencenet","provider_display":"InferenceNet","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.108,"output":0.35,"cache_read":0.032,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.11249999999999999,"output":0.375,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"glm-5.3-flash","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"reka","provider_display":"Reka","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","temperature","top_p","top_k","max_tokens","stop","seed","frequency_penalty","presence_penalty","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.12,"output":0.3,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"coreweave","provider_display":"CoreWeave","quantization":"nvfp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.12,"output":0.38,"cache_read":0.02,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"nextbit","provider_display":"NextBit","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":128000,"uptime_30m":95.23809523809523,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.78888106966924,"pricing":{"input":0.12,"output":0.48,"cache_read":0.04,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"phala","provider_display":"Phala","quantization":"nvfp4","discount":0.15,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.38335046248716,"pricing":{"input":0.1275,"output":0.425,"cache_read":0.0255,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"morph","provider_display":"Morph","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93006993006993,"pricing":{"input":0.13799999999999998,"output":0.226,"cache_read":0.049999999999999996,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"makora","provider_display":"Makora","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.41690962099126,"pricing":{"input":0.14,"output":0.47,"cache_read":0.024,"cache_write":null},"org":"z-ai","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"particle-ai","provider_display":"Particle AI","quantization":"nvfp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.7560975609756,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice","parallel_tool_calls","logprobs","top_logprobs","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"primeintellect","provider_display":"PrimeIntellect","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logit_bias","max_tokens","min_p","parallel_tool_calls","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"nebius","provider_display":"Nebius","quantization":"fp4","discount":0,"context_length":1024000,"max_completion_tokens":921600,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.51632047477746,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"zai-org/GLM-5.3-Flash","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"modal","provider_display":"Modal","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","stop","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.us-west.modal.direct/v1","model_id":"zai-org/GLM-5.3-Flash","doc_url":"https://modal.com/docs/guide/endpoints","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"baseten","provider_display":"BaseTen","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"zai-org/GLM-5.3-Flash","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"crusoe","provider_display":"Crusoe","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.79166666666667,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.80439121756487,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.72659176029963,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/glm-5p3-flash","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"friendli","provider_display":"Friendli","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.friendli.ai/serverless/v1","model_id":"zai-org/GLM-5.3-Flash","doc_url":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":83.33333333333334,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":89.91964937910883,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"zai-org/GLM-5.3-Flash","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1048575,"max_completion_tokens":943717,"uptime_30m":43.333333333333336,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.01388888888889,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"zai-org/GLM-5.3-Flash","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"parasail","provider_display":"Parasail","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.8756148981026,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5.3-flash","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"inceptron","provider_display":"Inceptron","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","stop","response_format","tools","tool_choice","logprobs","top_logprobs","frequency_penalty","logit_bias","parallel_tool_calls","presence_penalty","seed","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.16999999999999998,"output":0.6,"cache_read":0.06,"cache_write":0},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.inceptron.io/v1","model_id":"zai-org/GLM-5.3-Flash","doc_url":"https://docs.inceptron.io","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash:batch","name":"Z.ai: GLM 5.3 Flash (batch)","provider":"sail-research","provider_display":"Sail Research","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.049999999999999996,"output":0.18,"cache_read":0.01,"cache_write":null},"org":"z-ai","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3-flash:batch","name":"Z.ai: GLM 5.3 Flash (batch)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","structured_outputs","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.12,"output":0.39999999999999997,"cache_read":0.024,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":null,"model_id":"zai-org/GLM-5.3-Flash","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta/muse-spark-1.2-contributor","name":"Meta: Muse Spark 1.2 Contributor","provider":"meta","provider_display":"Meta","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.19999999999999998,"cache_read":0.002,"cache_write":null},"org":"meta","modelsdev":{"base_url":"https://api.meta.ai/v1","model_id":"muse-spark-1.2-contributor","doc_url":"https://dev.meta.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-08-05","knowledge_cutoff":null,"description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek: DeepSeek V4 Flash Vision Exp","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0,"context_length":1048575,"max_completion_tokens":943717,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.89177489177489,"pricing":{"input":0.44,"output":1.32,"cache_read":0.014,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-21","knowledge_cutoff":null,"description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":65,"agentic_index":47.5,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek: DeepSeek V4 Flash Vision Exp","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.44,"output":1.32,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-21","knowledge_cutoff":null,"description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":65,"agentic_index":47.5,"design_arena_best":null}},{"id":"tencent/hy-mt2-1.8b","name":"Tencent: Hy-MT2-1.8B","provider":"tencent","provider_display":"Tencent","quantization":"fp8","discount":0,"context_length":8192,"max_completion_tokens":4096,"uptime_30m":100,"supported_parameters":["temperature","stop","max_completion_tokens","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.044,"output":0.17700000000000002,"cache_read":null,"cache_write":null},"org":"tencent","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"tencent/hy-mt2-30b-a3b","name":"Tencent: Hy-MT2-30B-A3B","provider":"tencent","provider_display":"Tencent","quantization":"fp8","discount":0,"context_length":8192,"max_completion_tokens":4096,"uptime_30m":100,"supported_parameters":["temperature","stop","max_completion_tokens","max_tokens","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.72222222222223,"pricing":{"input":0.074,"output":0.295,"cache_read":null,"cache_write":null},"org":"tencent","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"tencent/hy-mt2-7b","name":"Tencent: Hy-MT2-7B","provider":"tencent","provider_display":"Tencent","quantization":"fp8","discount":0,"context_length":8192,"max_completion_tokens":4096,"uptime_30m":100,"supported_parameters":["temperature","stop","max_completion_tokens","max_tokens","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.65095986038395,"pricing":{"input":0.074,"output":0.295,"cache_read":null,"cache_write":null},"org":"tencent","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"relace","provider_display":"Relace","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.0703,"output":4.3843,"cache_read":0.0703,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"inferencenet","provider_display":"InferenceNet","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.08,"output":3.5999999999999996,"cache_read":0.07600000000000001,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"reka","provider_display":"Reka","quantization":"unknown","discount":0.3,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","temperature","top_p","top_k","max_tokens","stop","seed","frequency_penalty","presence_penalty","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.65181058495823,"pricing":{"input":0.14,"output":2.0999999999999996,"cache_read":0.105,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"makora","provider_display":"Makora","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.31350114416476,"pricing":{"input":0.14,"output":3,"cache_read":0.09999999999999999,"cache_write":null},"org":"z-ai","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"morph","provider_display":"Morph","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.0909090909091,"pricing":{"input":0.176,"output":1.544,"cache_read":0.06899999999999999,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"akashml","provider_display":"AkashML","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","max_tokens","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.19,"output":4.4,"cache_read":0.19,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"dekallm","provider_display":"DekaLLM","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logit_bias","max_tokens","presence_penalty","seed","stop","temperature","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.91902834008097,"pricing":{"input":0.25,"output":2.95,"cache_read":0.18,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.8,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","repetition_penalty","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.28,"output":0.88,"cache_read":0.052000000000000005,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"io-net","provider_display":"Io Net","quantization":"fp8","discount":0,"context_length":262124,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","response_format","logprobs","top_logprobs","seed","stop","min_p","top_k","top_p","presence_penalty","frequency_penalty","repetition_penalty","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.90917347865576,"pricing":{"input":0.33,"output":3.1999999999999997,"cache_read":0.31,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"sail-research","provider_display":"Sail Research","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","presence_penalty","seed","stop","temperature","top_k","top_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.5,"output":2,"cache_read":0.08,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"tenstorrent","provider_display":"Tenstorrent","quantization":"fp8","discount":0,"context_length":1044480,"max_completion_tokens":131072,"uptime_30m":50,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","seed","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.812382739212,"pricing":{"input":0.6,"output":2.5,"cache_read":0.09999999999999999,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.55,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.71890372452566,"pricing":{"input":0.63,"output":1.9800000000000002,"cache_read":0.117,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-5.3","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0.5,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.91589571068124,"pricing":{"input":0.7,"output":2.2,"cache_read":0.13,"cache_write":0},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"zai-org/GLM-5.3","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.5,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7,"output":2.2,"cache_read":0.13,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0.4,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.84,"output":2.64,"cache_read":0.156,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"decart","provider_display":"Decart","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.84,"output":2.69,"cache_read":0.19,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","tools","tool_choice","logprobs","top_logprobs","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.50372208436724,"pricing":{"input":0.9099999999999999,"output":2.8600000000000003,"cache_read":0.16899999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"glm-5.3","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":0,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":81.32611637347767,"pricing":{"input":0.98,"output":3.08,"cache_read":0.182,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/glm-5p3","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"primeintellect","provider_display":"PrimeIntellect","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","max_tokens","temperature","top_p","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.53739398612183,"pricing":{"input":0.98,"output":3.08,"cache_read":0.182,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.19,"output":3.74,"cache_read":0.238,"cache_write":null},"org":"z-ai","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"inceptron","provider_display":"Inceptron","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","stop","frequency_penalty","logit_bias","parallel_tool_calls","presence_penalty","seed","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":1.2,"output":2.2,"cache_read":0.14,"cache_write":0},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.inceptron.io/v1","model_id":"zai-org/GLM-5.3","doc_url":"https://docs.inceptron.io","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.7133666904932,"pricing":{"input":1.2,"output":4,"cache_read":0.19,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"friendli","provider_display":"Friendli","quantization":"unknown","discount":0.1,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.26,"output":3.9600000000000004,"cache_read":0.234,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.friendli.ai/serverless/v1","model_id":"zai-org/GLM-5.3","doc_url":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"mistral","provider_display":"Mistral","quantization":"nvfp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.9247554552295,"pricing":{"input":1.4,"output":4.4,"cache_read":0.14,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"baseten","provider_display":"BaseTen","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.14,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"zai-org/GLM-5.3","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"nebius","provider_display":"Nebius","quantization":"fp4","discount":0,"context_length":1024000,"max_completion_tokens":921600,"uptime_30m":0,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":94.29347826086956,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"zai-org/GLM-5.3","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"crusoe","provider_display":"Crusoe","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0.2,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.61389961389962,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1048575,"max_completion_tokens":943717,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"zai-org/GLM-5.3","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"modal","provider_display":"Modal","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","stop","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.us-west.modal.direct/v1","model_id":"zai-org/GLM-5.3","doc_url":"https://modal.com/docs/guide/endpoints","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/zai-org/glm-5.3","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5.3","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","seed","tools","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":65.90389016018307,"pricing":{"input":1.68,"output":5.28,"cache_read":0.312,"cache_write":2.0999999999999996},"org":"z-ai","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","provider":"modelrun","provider_display":"ModelRun","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":524288,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","presence_penalty","repetition_penalty","frequency_penalty","stop","top_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.0999999999999996,"output":6.6000000000000005,"cache_read":0.39999999999999997,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3:fast","name":"Z.ai: GLM 5.3 (fast)","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":86.20689655172413,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.49170437405732,"pricing":{"input":2.0999999999999996,"output":6.6000000000000005,"cache_read":0.39,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/glm-5p3","doc_url":"https://fireworks.ai/docs/","confidence":"medium","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3:fast","name":"Z.ai: GLM 5.3 (fast)","provider":"baseten","provider_display":"BaseTen","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.14651368049427,"pricing":{"input":2.0999999999999996,"output":6.6000000000000005,"cache_read":0.21,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"zai-org/GLM-5.3","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"medium","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.3:batch","name":"Z.ai: GLM 5.3 (batch)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0.375,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.44999999999999996,"output":2,"cache_read":0.09999999999999999,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":null,"model_id":"zai-org/GLM-5.3","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"darkbloom","provider_display":"Darkbloom","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.29411764705883,"pricing":{"input":0.035,"output":2.2,"cache_read":0.0175,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"chutes","provider_display":"Chutes","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.039,"output":1.25,"cache_read":0.0039000000000000003,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"Qwen/Qwen3.8-27B-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"near-ai","provider_display":"Near AI","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","max_tokens","stop","seed","structured_outputs","tools","tool_choice","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.04,"output":1.35,"cache_read":0.018,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"ionstream","provider_display":"Ionstream","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":86.66666666666667,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.33962264150944,"pricing":{"input":0.04,"output":1.95,"cache_read":0.02,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"reka","provider_display":"Reka","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","temperature","top_p","top_k","max_tokens","stop","seed","frequency_penalty","presence_penalty","repetition_penalty","min_p","logit_bias","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.61111111111111,"pricing":{"input":0.04,"output":2.2,"cache_read":0.02,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"modal","provider_display":"Modal","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.04,"output":2.3,"cache_read":0.02,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"dekallm","provider_display":"DekaLLM","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logit_bias","max_tokens","presence_penalty","seed","stop","temperature","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.21875,"pricing":{"input":0.04,"output":2.5,"cache_read":0.02,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"tenstorrent","provider_display":"Tenstorrent","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":96.66666666666667,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","seed","max_tokens","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.84962406015038,"pricing":{"input":0.15,"output":1.5,"cache_read":0.03,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","response_format","logprobs","top_logprobs","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":93.69918699186992,"pricing":{"input":0.18,"output":2.5,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"modelrun","provider_display":"ModelRun","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","presence_penalty","repetition_penalty","frequency_penalty","stop","top_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":2.5,"cache_read":0.09,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.86111111111111,"pricing":{"input":0.19999999999999998,"output":2.5,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"akashml","provider_display":"AkashML","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","repetition_penalty","seed","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.22499999999999998,"output":1.9800000000000002,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.78432782171099,"pricing":{"input":0.24,"output":2.2,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":90,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.11426040744021,"pricing":{"input":0.39999999999999997,"output":3,"cache_read":0.15,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.42,"output":3,"cache_read":0.08499999999999999,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3.8-27b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":87.44619799139168,"pricing":{"input":0.425,"output":2.5500000000000003,"cache_read":0.08499999999999999,"cache_write":0.53125},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":96.74185463659147,"pricing":{"input":0.44999999999999996,"output":3.1999999999999997,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/qwen/qwen3.8-27b","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.44999999999999996,"output":3.1999999999999997,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","provider":"cerebras","provider_display":"Cerebras","quantization":"fp16","discount":0,"context_length":65536,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","logprobs","top_logprobs","frequency_penalty","presence_penalty","logit_bias","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.9900000000000001,"output":1.49,"cache_read":0.9900000000000001,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.1,"coding_index":68.1,"agentic_index":45.8,"design_arena_best":null,"arena_text":1437.752104573814,"arena_text_rank":100,"arena_text_rating_lower":1432.6435966790054,"arena_text_rating_upper":1442.8606124686223,"arena_text_vote_count":23294,"arena_text_date":"2026-10-15","arena_creative_writing":1366.416329225688,"arena_creative_writing_rank":160,"arena_creative_writing_rating_lower":1356.846099071079,"arena_creative_writing_rating_upper":1375.9865593802974,"arena_creative_writing_vote_count":4668,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.7-flash:flex","name":"Google: Gemini 3.7 Flash (flex)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":0,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":43.98249452954048,"pricing":{"input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.0208333333333333},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.7-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":"2026-03","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.1,"coding_index":76.1,"agentic_index":35.2,"design_arena_best":{"category":"dataviz","elo":1318,"win_rate":55.4,"rank":11},"arena_text":1487.5878753892953,"arena_text_rank":17,"arena_text_rating_lower":1482.7056648473051,"arena_text_rating_upper":1492.4700859312854,"arena_text_vote_count":27232,"arena_text_date":"2026-10-15","arena_creative_writing":1490.973144146456,"arena_creative_writing_rank":5,"arena_creative_writing_rating_lower":1482.129415167425,"arena_creative_writing_rating_upper":1499.816873125487,"arena_creative_writing_vote_count":6003,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.7-flash","name":"Google: Gemini 3.7 Flash","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.0416666666666667},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3.7-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":"2026-03","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.1,"coding_index":76.1,"agentic_index":35.2,"design_arena_best":{"category":"dataviz","elo":1318,"win_rate":55.4,"rank":11},"arena_text":1487.5878753892953,"arena_text_rank":17,"arena_text_rating_lower":1482.7056648473051,"arena_text_rating_upper":1492.4700859312854,"arena_text_vote_count":27232,"arena_text_date":"2026-10-15","arena_creative_writing":1490.973144146456,"arena_creative_writing_rank":5,"arena_creative_writing_rating_lower":1482.129415167425,"arena_creative_writing_rating_upper":1499.816873125487,"arena_creative_writing_vote_count":6003,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.7-flash:priority","name":"Google: Gemini 3.7 Flash (priority)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.35,"output":6.75,"cache_read":0.135,"cache_write":0.075},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.7-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":"2026-03","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.1,"coding_index":76.1,"agentic_index":35.2,"design_arena_best":{"category":"dataviz","elo":1318,"win_rate":55.4,"rank":11},"arena_text":1487.5878753892953,"arena_text_rank":17,"arena_text_rating_lower":1482.7056648473051,"arena_text_rating_upper":1492.4700859312854,"arena_text_vote_count":27232,"arena_text_date":"2026-10-15","arena_creative_writing":1490.973144146456,"arena_creative_writing_rank":5,"arena_creative_writing_rating_lower":1482.129415167425,"arena_creative_writing_rating_upper":1499.816873125487,"arena_creative_writing_vote_count":6003,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.7-flash:batch","name":"Google: Gemini 3.7 Flash (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0.5,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.0416666666666667},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.7-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":"2026-03","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.1,"coding_index":76.1,"agentic_index":35.2,"design_arena_best":{"category":"dataviz","elo":1318,"win_rate":55.4,"rank":11},"arena_text":1487.5878753892953,"arena_text_rank":17,"arena_text_rating_lower":1482.7056648473051,"arena_text_rating_upper":1492.4700859312854,"arena_text_vote_count":27232,"arena_text_date":"2026-10-15","arena_creative_writing":1490.973144146456,"arena_creative_writing_rank":5,"arena_creative_writing_rating_lower":1482.129415167425,"arena_creative_writing_rating_upper":1499.816873125487,"arena_creative_writing_vote_count":6003,"arena_creative_writing_date":"2026-10-15"}},{"id":"bytedance-seed/seed-2-1-turbo","name":"ByteDance Seed: Seed 2.1 Turbo","provider":"seed","provider_display":"Seed","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","stop","tools","response_format","structured_outputs","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":98.72611464968153,"pricing":{"input":0.5,"output":2.5,"cache_read":null,"cache_write":null},"org":"bytedance","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-23","knowledge_cutoff":null,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.venice.ai","reasoning_options":[],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen: Qwen3.8 2.4T A95B","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":6,"cache_read":0.25,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3.8-2.4t-a95b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-08-12","knowledge_cutoff":null,"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"qwen3.8-max","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.9,"coding_index":71.9,"agentic_index":50.1,"design_arena_best":null}},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen: Qwen3.8 2.4T A95B","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","tools","tool_choice","logprobs","top_logprobs","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-12","knowledge_cutoff":null,"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"qwen3.8-max","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.9,"coding_index":71.9,"agentic_index":50.1,"design_arena_best":null}},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen: Qwen3.8 2.4T A95B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":6,"cache_read":0.25,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3.8-2.4T-A95B","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-12","knowledge_cutoff":null,"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"qwen3.8-max","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.9,"coding_index":71.9,"agentic_index":50.1,"design_arena_best":null}},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen: Qwen3.8 2.4T A95B","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0.2,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":6,"cache_read":0.25,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-12","knowledge_cutoff":null,"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"qwen3.8-max","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.9,"coding_index":71.9,"agentic_index":50.1,"design_arena_best":null}},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen: Qwen3.8 2.4T A95B","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1010000,"max_completion_tokens":909000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.70817120622569,"pricing":{"input":2,"output":6,"cache_read":0.25,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-12","knowledge_cutoff":null,"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"qwen3.8-max","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.9,"coding_index":71.9,"agentic_index":50.1,"design_arena_best":null}},{"id":"bytedance-seed/seed-2.0-code","name":"ByteDance Seed: Seed-2.0-Code","provider":"seed","provider_display":"Seed","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.5,"output":3,"cache_read":null,"cache_write":null},"org":"bytedance","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-14","knowledge_cutoff":null,"description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"relace","provider_display":"Relace","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","stop","max_tokens","logit_bias","frequency_penalty","presence_penalty","repetition_penalty","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.16434540389972,"pricing":{"input":0.1035,"output":8,"cache_read":0.09999999999999999,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"wafer","provider_display":"Wafer","quantization":"mxfp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.5042492917847,"pricing":{"input":0.11499999999999999,"output":4.300000000000001,"cache_read":0.11,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"ionstream","provider_display":"Ionstream","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_p","top_k","frequency_penalty","presence_penalty","stop","seed","logit_bias","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.86111111111111,"pricing":{"input":0.37,"output":2.9299999999999997,"cache_read":0.088,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.66,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.4488,"output":1.3464,"cache_read":0.01428,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.80334728033473,"pricing":{"input":0.5808,"output":1.7424,"cache_read":0.05808,"cache_write":null},"org":"deepseek","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0.5,"context_length":1024000,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.66,"output":1.9800000000000002,"cache_read":0.022,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"deepseek","provider_display":"DeepSeek","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","logprobs","top_logprobs","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.66,"output":1.9800000000000002,"cache_read":0.022,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"sail-research","provider_display":"Sail Research","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.675,"output":1.2,"cache_read":0.0975,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0.34,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":false,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.9569999999999999,"output":2.8776,"cache_read":0.099,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.25,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.9900000000000001,"output":2.9699999999999998,"cache_read":0.032999999999999995,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-v4-pro-0813","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.2,"context_length":1048575,"max_completion_tokens":943717,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.30555555555556,"pricing":{"input":1.0559999999999998,"output":3.168,"cache_read":0.035199999999999995,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"dekallm","provider_display":"DekaLLM","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logit_bias","max_tokens","presence_penalty","seed","stop","temperature","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.03264812575574,"pricing":{"input":1.08,"output":3.8,"cache_read":0.18,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.78783592644979,"pricing":{"input":1.31,"output":3.9600000000000004,"cache_read":0.044,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"baseten","provider_display":"BaseTen","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.27891156462584,"pricing":{"input":1.32,"output":3.9600000000000004,"cache_read":0.13199999999999998,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":null,"description":"Flagship DeepSeek model for coding, reasoning, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.32,"output":3.9600000000000004,"cache_read":0.13199999999999998,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":979000,"max_completion_tokens":881100,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":59.964093357271096,"pricing":{"input":1.32,"output":3.9600000000000004,"cache_read":0.04,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.48320413436691,"pricing":{"input":1.32,"output":3.9600000000000004,"cache_read":0.044,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.74170783345096,"pricing":{"input":1.32,"output":3.9600000000000004,"cache_read":0.13,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","tools","tool_choice","logprobs","top_logprobs","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.32,"output":3.9600000000000004,"cache_read":0.044,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"deepseek-v4-pro-0813","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.19354838709677,"pricing":{"input":1.32,"output":3.9600000000000004,"cache_read":0.044,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.82876712328768,"pricing":{"input":1.32,"output":3.9600000000000004,"cache_read":0.044,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/deepseek-ai/deepseek-v4-pro-0813","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":32768,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":94.11764705882352,"pricing":{"input":1.6500000000000001,"output":4.95,"cache_read":0.165,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-v4-pro-0813","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":null,"description":"Flagship DeepSeek model for coding, reasoning, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.1,"coding_index":68.8,"agentic_index":41.3,"design_arena_best":null}},{"id":"x-ai/grok-4.6","name":"SpaceXAI: Grok 4.6","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":500000,"max_completion_tokens":450000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.9290276792051,"pricing":{"input":2,"output":6,"cache_read":0.5,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"context_price_tiers":[{"above_tokens":200000,"input":4,"output":12,"cache_read":1,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"grok-4.6","doc_url":"https://docs.x.ai/docs/models","confidence":"high","source":"models.dev","release_date":"2026-08-12","knowledge_cutoff":"2026-02-01","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":44.3,"coding_index":76.8,"agentic_index":53,"design_arena_best":{"category":"gamedev","elo":1294,"win_rate":54,"rank":20},"arena_text":1454.4891469812887,"arena_text_rank":73,"arena_text_rating_lower":1449.6545088049184,"arena_text_rating_upper":1459.3237851576594,"arena_text_vote_count":28965,"arena_text_date":"2026-10-15","arena_creative_writing":1441.9162652815512,"arena_creative_writing_rank":57,"arena_creative_writing_rating_lower":1433.4392925071782,"arena_creative_writing_rating_upper":1450.3932380559243,"arena_creative_writing_vote_count":6434,"arena_creative_writing_date":"2026-10-15"}},{"id":"x-ai/grok-4.6","name":"SpaceXAI: Grok 4.6","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":500000,"max_completion_tokens":450000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.2,"output":6.6000000000000005,"cache_read":0.55,"cache_write":0},"org":"xai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":44.3,"coding_index":76.8,"agentic_index":53,"design_arena_best":{"category":"gamedev","elo":1294,"win_rate":54,"rank":20},"arena_text":1454.4891469812887,"arena_text_rank":73,"arena_text_rating_lower":1449.6545088049184,"arena_text_rating_upper":1459.3237851576594,"arena_text_vote_count":28965,"arena_text_date":"2026-10-15","arena_creative_writing":1441.9162652815512,"arena_creative_writing_rank":57,"arena_creative_writing_rating_lower":1433.4392925071782,"arena_creative_writing_rating_upper":1450.3932380559243,"arena_creative_writing_vote_count":6434,"arena_creative_writing_date":"2026-10-15"}},{"id":"x-ai/grok-4.6:priority","name":"SpaceXAI: Grok 4.6 (priority)","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":500000,"max_completion_tokens":450000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":4,"output":12,"cache_read":1,"cache_write":null},"org":"xai","subscription":true,"modelsdev":{"base_url":null,"model_id":"grok-4.6","doc_url":"https://docs.x.ai/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-08-12","knowledge_cutoff":"2026-02-01","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":44.3,"coding_index":76.8,"agentic_index":53,"design_arena_best":{"category":"gamedev","elo":1294,"win_rate":54,"rank":20},"arena_text":1454.4891469812887,"arena_text_rank":73,"arena_text_rating_lower":1449.6545088049184,"arena_text_rating_upper":1459.3237851576594,"arena_text_vote_count":28965,"arena_text_date":"2026-10-15","arena_creative_writing":1441.9162652815512,"arena_creative_writing_rank":57,"arena_creative_writing_rating_lower":1433.4392925071782,"arena_creative_writing_rating_upper":1450.3932380559243,"arena_creative_writing_vote_count":6434,"arena_creative_writing_date":"2026-10-15"}},{"id":"liquid/lfm-2.5-2.6b","name":"LiquidAI: LFM2.5-2.6B","provider":"liquid","provider_display":"Liquid","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":8192,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","max_completion_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.35,"output":0.5,"cache_read":0.04,"cache_write":null},"org":"liquid","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":7.7,"agentic_index":null,"design_arena_best":null}},{"id":"nvidia/nemotron-3.5-lightning","name":"NVIDIA: Nemotron 3.5 Lightning","provider":"darkbloom","provider_display":"Darkbloom","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.81549815498155,"pricing":{"input":0.024999999999999998,"output":0.12,"cache_read":0.012499999999999999,"cache_write":null},"org":"nvidia","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.9,"coding_index":26.8,"agentic_index":3.5,"design_arena_best":null}},{"id":"nvidia/nemotron-3.5-lightning","name":"NVIDIA: Nemotron 3.5 Lightning","provider":"io-net","provider_display":"Io Net","quantization":"unknown","discount":0.33,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","logprobs","top_logprobs","tools","response_format","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.82547993019197,"pricing":{"input":0.046900000000000004,"output":0.134,"cache_read":0.023450000000000002,"cache_write":null},"org":"nvidia","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.9,"coding_index":26.8,"agentic_index":3.5,"design_arena_best":null}},{"id":"nvidia/nemotron-3.5-lightning","name":"NVIDIA: Nemotron 3.5 Lightning","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","structured_outputs","response_format","tools","tool_choice","logit_bias"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.23011120615911,"pricing":{"input":0.06,"output":0.16,"cache_read":0.03,"cache_write":null},"org":"nvidia","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.9,"coding_index":26.8,"agentic_index":3.5,"design_arena_best":null}},{"id":"nvidia/nemotron-3.5-lightning","name":"NVIDIA: Nemotron 3.5 Lightning","provider":"coreweave","provider_display":"CoreWeave","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.07,"output":0.19999999999999998,"cache_read":0.04,"cache_write":null},"org":"nvidia","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.9,"coding_index":26.8,"agentic_index":3.5,"design_arena_best":null}},{"id":"sakana/sakana-namazu","name":"Sakana: Sakana Namazu","provider":"sakana","provider_display":"Sakana AI","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","structured_outputs","web_search_options","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.95,"output":4,"cache_read":0.15,"cache_write":null},"org":"sakana","modelsdev":{"base_url":"https://api.sakana.ai/v1","model_id":"sakana-namazu","doc_url":"https://console.sakana.ai/models","confidence":"high","source":"models.dev","release_date":"2026-08-03","knowledge_cutoff":null,"description":"Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"upstage/solar-pro4","name":"Upstage: Solar Pro 4","provider":"upstage","provider_display":"Upstage","quantization":"unknown","discount":0.5,"context_length":524288,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","response_format","structured_outputs","tools","tool_choice","top_p","frequency_penalty","presence_penalty","parallel_tool_calls","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.6,"cache_read":0.03,"cache_write":null},"org":"upstage","zdr":true,"modelsdev":{"base_url":"https://api.upstage.ai/v1/solar","model_id":"solar-pro4","doc_url":"https://developers.upstage.ai/docs/apis/chat","confidence":"high","source":"models.dev","release_date":"2026-08-06","knowledge_cutoff":"2026-02","description":"Upstage's flagship model, specialized for agentic use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.2,"coding_index":52.7,"agentic_index":28.8,"design_arena_best":{"category":"codecategories","elo":1180,"win_rate":39,"rank":68},"arena_text":1386.425816378497,"arena_text_rank":183,"arena_text_rating_lower":1381.111884284797,"arena_text_rating_upper":1391.739748472197,"arena_text_vote_count":21281,"arena_text_date":"2026-10-15","arena_creative_writing":1309.258294936353,"arena_creative_writing_rank":223,"arena_creative_writing_rating_lower":1299.324560938517,"arena_creative_writing_rating_upper":1319.192028934189,"arena_creative_writing_vote_count":4615,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta/muse-glimmer-30b","name":"Meta: Muse Glimmer 30B","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":69.97084548104957,"pricing":{"input":0.35,"output":1.5,"cache_read":0.04,"cache_write":null},"org":"meta","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":"Apache 2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.3,"coding_index":49,"agentic_index":8.5,"design_arena_best":{"category":"uicomponent","elo":1206,"win_rate":40,"rank":58}}},{"id":"meta/muse-spark-1.2","name":"Meta: Muse Spark 1.2","provider":"meta","provider_display":"Meta","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":null},"org":"meta","modelsdev":{"base_url":"https://api.meta.ai/v1","model_id":"muse-spark-1.2","doc_url":"https://dev.meta.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-08-05","knowledge_cutoff":null,"description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39.6,"coding_index":72.2,"agentic_index":43.2,"design_arena_best":{"category":"dataviz","elo":1333,"win_rate":57.4,"rank":8},"arena_text":1493.0608667270417,"arena_text_rank":12,"arena_text_rating_lower":1485.8976160964726,"arena_text_rating_upper":1500.224117357611,"arena_text_vote_count":8248,"arena_text_date":"2026-10-15","arena_creative_writing":1444.8460451758367,"arena_creative_writing_rank":51,"arena_creative_writing_rating_lower":1429.5756992570816,"arena_creative_writing_rating_upper":1460.1163910945916,"arena_creative_writing_vote_count":1705,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"wafer","provider_display":"Wafer","quantization":"nvfp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.046,"output":0.3,"cache_read":0.045,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"relace","provider_display":"Relace","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","tools","temperature","top_p","top_k","min_p","stop","max_tokens","logit_bias","frequency_penalty","presence_penalty","repetition_penalty","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.65277777777779,"pricing":{"input":0.0509,"output":0.1487,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.878,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.05368,"output":0.16104,"cache_read":0.001708,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731:fast","name":"DeepSeek: DeepSeek V4 Flash 0731 (fast)","provider":"wafer","provider_display":"Wafer","quantization":"nvfp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","logit_bias","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.08499999999999999,"output":0.22999999999999998,"cache_read":0.08,"cache_write":null},"org":"deepseek","open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"reka","provider_display":"Reka","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","temperature","top_p","top_k","max_tokens","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.28,"cache_read":0.04,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","tools","tool_choice","logprobs","top_logprobs","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.119,"output":0.238,"cache_read":0.0238,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"deepseek-v4-flash-0731","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"baseten","provider_display":"BaseTen","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.13,"output":0.26,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.13,"output":0.26,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-v4-flash-0731","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.13,"output":0.28,"cache_read":0.07,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"inceptron","provider_display":"Inceptron","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","stop","frequency_penalty","logit_bias","parallel_tool_calls","presence_penalty","seed","response_format","tools","tool_choice","logprobs","top_logprobs","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.13,"output":0.40890000000000004,"cache_read":0.027,"cache_write":0},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.inceptron.io/v1","model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","doc_url":"https://docs.inceptron.io","confidence":"high","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.7,"context_length":1024000,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","tools","tool_choice","logprobs","top_logprobs","max_tokens","temperature","top_p","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.13199999999999998,"output":0.396,"cache_read":0.004200000000000001,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice","parallel_tool_calls","logprobs","top_logprobs","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.14,"output":0.28,"cache_read":0.07,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.14,"output":0.28,"cache_read":0.049999999999999996,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"sail-research","provider_display":"Sail Research","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","presence_penalty","seed","stop","temperature","top_k","top_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.3,"cache_read":0.041999999999999996,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","top_k","frequency_penalty","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.7134670487106,"pricing":{"input":0.176,"output":0.5279999999999999,"cache_read":0.017599999999999998,"cache_write":null},"org":"deepseek","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"deepseek-v4-flash-0731","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","response_format","logprobs","top_logprobs","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":0.6,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.22,"output":0.66,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.35,"context_length":1048575,"max_completion_tokens":943717,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.286,"output":0.858,"cache_read":0.0091,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0.3,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.308,"output":0.9239999999999999,"cache_read":0.0196,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.07,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","response_format","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.4092,"output":1.2275999999999998,"cache_read":0.02604,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-v4-flash-0731","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.64953271028037,"pricing":{"input":0.44,"output":1.32,"cache_read":0.028,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.44,"output":1.32,"cache_read":0.014,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/deepseek-ai/deepseek-v4-flash-0731","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":69.1,"agentic_index":41,"design_arena_best":{"category":"website","elo":1236,"win_rate":46.7,"rank":51}}},{"id":"qwen/qwen3.7-flash","name":"Qwen: Qwen3.7 Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":983616,"uptime_1d":100,"pricing":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038000000000000006},"org":"qwen","subscription":true,"context_price_tiers":[{"above_tokens":32000,"input":0.1,"output":0.4,"cache_read":0.02,"cache_write":0.125},{"above_tokens":256000,"input":0.2,"output":0.8,"cache_read":0.04,"cache_write":0.25}],"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.7-flash","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-07-15","knowledge_cutoff":null,"description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null},{"id":"anthropic/claude-opus-5","name":"Anthropic: Claude Opus 5","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-24","knowledge_cutoff":"2026-05","description":"Strongest Claude Opus model for coding, agents, and professional work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.8,"coding_index":78,"agentic_index":56.5,"design_arena_best":{"category":"asciiart","elo":1358,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-5","name":"Anthropic: Claude Opus 5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","response_format","tool_choice","tools","verbosity","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-24","knowledge_cutoff":"2026-05","description":"Strongest Claude Opus model for coding, agents, and professional work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.8,"coding_index":78,"agentic_index":56.5,"design_arena_best":{"category":"asciiart","elo":1358,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-5","name":"Anthropic: Claude Opus 5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"modelsdev":{"base_url":null,"model_id":"us.anthropic.claude-opus-5","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-07-24","knowledge_cutoff":"2026-05","description":"Strongest Claude Opus model for coding, agents, and professional work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.8,"coding_index":78,"agentic_index":56.5,"design_arena_best":{"category":"asciiart","elo":1358,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-5","name":"Anthropic: Claude Opus 5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-opus-5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-07-24","knowledge_cutoff":"2026-05","description":"Strongest Claude Opus model for coding, agents, and professional work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.8,"coding_index":78,"agentic_index":56.5,"design_arena_best":{"category":"asciiart","elo":1358,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-5","name":"Anthropic: Claude Opus 5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-opus-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"high","source":"models.dev","release_date":"2026-07-24","knowledge_cutoff":"2026-05","description":"Strongest Claude Opus model for coding, agents, and professional work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.8,"coding_index":78,"agentic_index":56.5,"design_arena_best":{"category":"asciiart","elo":1358,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-5:fast","name":"Anthropic: Claude Opus 5 (fast)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-opus-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"medium","source":"models.dev","release_date":"2026-07-24","knowledge_cutoff":"2026-05","description":"Strongest Claude Opus model for coding, agents, and professional work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.8,"coding_index":78,"agentic_index":56.5,"design_arena_best":{"category":"asciiart","elo":1358,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-5:batch","name":"Anthropic: Claude Opus 5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-opus-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"medium","source":"models.dev","release_date":"2026-07-24","knowledge_cutoff":"2026-05","description":"Strongest Claude Opus model for coding, agents, and professional work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":50.8,"coding_index":78,"agentic_index":56.5,"design_arena_best":{"category":"asciiart","elo":1358,"win_rate":68.9,"rank":1}}},{"id":"inclusionai/ling-3.0-flash","name":"inclusionAI: Ling 3.0 Flash","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0.65,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.72222222222223,"pricing":{"input":0.020999999999999998,"output":0.063,"cache_read":0.004200000000000001,"cache_write":null},"org":"inclusionai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"inclusionai/ling-3.0-flash","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-07-23","knowledge_cutoff":null,"description":"Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":50.6,"agentic_index":19.3,"design_arena_best":null}},{"id":"poolside/laguna-s-2.1","name":"Poolside: Laguna S 2.1","provider":"poolside","provider_display":"Poolside","quantization":"fp4","discount":0.1,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","temperature","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.7822931785196,"pricing":{"input":0.09,"output":0.18,"cache_read":0.009,"cache_write":0},"org":"poolside","modelsdev":{"base_url":"https://inference.poolside.ai/v1","model_id":"poolside/laguna-s-2.1","doc_url":"https://platform.poolside.ai","confidence":"high","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":null,"description":"Agentic coding model from Poolside in the XS size class for local deployment","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"google/gemini-3.6-flash:flex","name":"Google: Gemini 3.6 Flash (flex)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":86.20689655172413,"pricing":{"input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.0208333333333333},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.6-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":34,"coding_index":69.2,"agentic_index":29,"design_arena_best":{"category":"website","elo":1299,"win_rate":55.4,"rank":16},"arena_text":1482.7020039923352,"arena_text_rank":23,"arena_text_rating_lower":1478.278787574737,"arena_text_rating_upper":1487.1252204099333,"arena_text_vote_count":36122,"arena_text_date":"2026-10-15","arena_creative_writing":1470.964561412504,"arena_creative_writing_rank":15,"arena_creative_writing_rating_lower":1462.9783608694165,"arena_creative_writing_rating_upper":1478.9507619555916,"arena_creative_writing_vote_count":7583,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.6-flash","name":"Google: Gemini 3.6 Flash","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.0416666666666667},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3.6-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":34,"coding_index":69.2,"agentic_index":29,"design_arena_best":{"category":"website","elo":1299,"win_rate":55.4,"rank":16},"arena_text":1482.7020039923352,"arena_text_rank":23,"arena_text_rating_lower":1478.278787574737,"arena_text_rating_upper":1487.1252204099333,"arena_text_vote_count":36122,"arena_text_date":"2026-10-15","arena_creative_writing":1470.964561412504,"arena_creative_writing_rank":15,"arena_creative_writing_rating_lower":1462.9783608694165,"arena_creative_writing_rating_upper":1478.9507619555916,"arena_creative_writing_vote_count":7583,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.6-flash:priority","name":"Google: Gemini 3.6 Flash (priority)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.35,"output":6.75,"cache_read":0.135,"cache_write":0.075},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.6-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":34,"coding_index":69.2,"agentic_index":29,"design_arena_best":{"category":"website","elo":1299,"win_rate":55.4,"rank":16},"arena_text":1482.7020039923352,"arena_text_rank":23,"arena_text_rating_lower":1478.278787574737,"arena_text_rating_upper":1487.1252204099333,"arena_text_vote_count":36122,"arena_text_date":"2026-10-15","arena_creative_writing":1470.964561412504,"arena_creative_writing_rank":15,"arena_creative_writing_rating_lower":1462.9783608694165,"arena_creative_writing_rating_upper":1478.9507619555916,"arena_creative_writing_vote_count":7583,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.6-flash:batch","name":"Google: Gemini 3.6 Flash (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.0416666666666667},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.6-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":34,"coding_index":69.2,"agentic_index":29,"design_arena_best":{"category":"website","elo":1299,"win_rate":55.4,"rank":16},"arena_text":1482.7020039923352,"arena_text_rank":23,"arena_text_rating_lower":1478.278787574737,"arena_text_rating_upper":1487.1252204099333,"arena_text_vote_count":36122,"arena_text_date":"2026-10-15","arena_creative_writing":1470.964561412504,"arena_creative_writing_rank":15,"arena_creative_writing_rating_lower":1462.9783608694165,"arena_creative_writing_rating_upper":1478.9507619555916,"arena_creative_writing_vote_count":7583,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.5-flash-lite:flex","name":"Google: Gemini 3.5 Flash Lite (flex)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":91.06344950848973,"pricing":{"input":0.15,"output":1.25,"cache_read":0.015,"cache_write":0.0416666666666667},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.7,"coding_index":49.3,"agentic_index":14.3,"design_arena_best":null,"arena_text":1454.7574024087119,"arena_text_rank":72,"arena_text_rating_lower":1450.2850641771397,"arena_text_rating_upper":1459.2297406402843,"arena_text_vote_count":35851,"arena_text_date":"2026-10-15","arena_creative_writing":1435.9595123657105,"arena_creative_writing_rank":65,"arena_creative_writing_rating_lower":1427.981400921513,"arena_creative_writing_rating_upper":1443.937623809908,"arena_creative_writing_vote_count":7473,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.5-flash-lite","name":"Google: Gemini 3.5 Flash Lite","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.0833333333333333},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.7,"coding_index":49.3,"agentic_index":14.3,"design_arena_best":null,"arena_text":1454.7574024087119,"arena_text_rank":72,"arena_text_rating_lower":1450.2850641771397,"arena_text_rating_upper":1459.2297406402843,"arena_text_vote_count":35851,"arena_text_date":"2026-10-15","arena_creative_writing":1435.9595123657105,"arena_creative_writing_rank":65,"arena_creative_writing_rating_lower":1427.981400921513,"arena_creative_writing_rating_upper":1443.937623809908,"arena_creative_writing_vote_count":7473,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.5-flash-lite:priority","name":"Google: Gemini 3.5 Flash Lite (priority)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.54,"output":4.5,"cache_read":0.054,"cache_write":0.15},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.7,"coding_index":49.3,"agentic_index":14.3,"design_arena_best":null,"arena_text":1454.7574024087119,"arena_text_rank":72,"arena_text_rating_lower":1450.2850641771397,"arena_text_rating_upper":1459.2297406402843,"arena_text_vote_count":35851,"arena_text_date":"2026-10-15","arena_creative_writing":1435.9595123657105,"arena_creative_writing_rank":65,"arena_creative_writing_rating_lower":1427.981400921513,"arena_creative_writing_rating_upper":1443.937623809908,"arena_creative_writing_vote_count":7473,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.5-flash-lite:batch","name":"Google: Gemini 3.5 Flash Lite (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.15,"output":1.25,"cache_read":0.015,"cache_write":null},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.7,"coding_index":49.3,"agentic_index":14.3,"design_arena_best":null,"arena_text":1454.7574024087119,"arena_text_rank":72,"arena_text_rating_lower":1450.2850641771397,"arena_text_rating_upper":1459.2297406402843,"arena_text_vote_count":35851,"arena_text_date":"2026-10-15","arena_creative_writing":1435.9595123657105,"arena_creative_writing_rank":65,"arena_creative_writing_rating_lower":1427.981400921513,"arena_creative_writing_rating_upper":1443.937623809908,"arena_creative_writing_vote_count":7473,"arena_creative_writing_date":"2026-10-15"}},{"id":"meituan/longcat-2.0","name":"Meituan: LongCat 2.0","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0.6,"context_length":1048756,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","stop","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.7062404870624,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"meituan","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-30","knowledge_cutoff":null,"description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":19.1,"coding_index":45.3,"agentic_index":14,"design_arena_best":null}},{"id":"thinkingmachines/inkling","name":"Thinking Machines: Inkling","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":524288,"max_completion_tokens":471859,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.72776769509983,"pricing":{"input":1,"output":4.05,"cache_read":0.16999999999999998,"cache_write":null},"org":"thinkingmachines","zdr":true,"modelsdev":{"base_url":null,"model_id":"thinkingmachines/Inkling","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-07-15","knowledge_cutoff":null,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.5,"coding_index":52.1,"agentic_index":22.5,"design_arena_best":{"category":"website","elo":1224,"win_rate":44.7,"rank":58},"arena_text":1440.8717396141749,"arena_text_rank":97,"arena_text_rating_lower":1436.5585433735794,"arena_text_rating_upper":1445.1849358547706,"arena_text_vote_count":40648,"arena_text_date":"2026-10-15","arena_creative_writing":1380.9974874241316,"arena_creative_writing_rank":144,"arena_creative_writing_rating_lower":1373.523053280632,"arena_creative_writing_rating_upper":1388.4719215676314,"arena_creative_writing_vote_count":8748,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3:fast","name":"MoonshotAI: Kimi K3 (fast)","provider":"wafer","provider_display":"Wafer","quantization":"mxfp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","logit_bias","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.171,"output":22,"cache_read":0.16999999999999998,"cache_write":null},"org":"moonshot","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"relace","provider_display":"Relace","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","repetition_penalty","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.57716701902748,"pricing":{"input":0.1719,"output":9.338799999999999,"cache_read":0.16999999999999998,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"sail-research","provider_display":"Sail Research","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","presence_penalty","seed","stop","temperature","top_k","top_p","response_format","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.22999999999999998,"output":11,"cache_read":0.11499999999999999,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"inferencenet","provider_display":"InferenceNet","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.23900000000000002,"output":10.8,"cache_read":0.21,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3:fast","name":"MoonshotAI: Kimi K3 (fast)","provider":"inferencenet","provider_display":"InferenceNet","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","logit_bias","response_format","structured_outputs","repetition_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.5,"output":11.879999999999999,"cache_read":0.35,"cache_write":null},"org":"moonshot","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"makora","provider_display":"Makora","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.91755976916735,"pricing":{"input":0.5,"output":13,"cache_read":0.19999999999999998,"cache_write":null},"org":"moonshot","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"akashml","provider_display":"AkashML","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","max_tokens","structured_outputs","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.55072463768117,"pricing":{"input":1.2,"output":14,"cache_read":1.2,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"morph","provider_display":"Morph","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.92887624466572,"pricing":{"input":1.278,"output":14.626,"cache_read":0.36,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"decart","provider_display":"Decart","quantization":"mxfp4","discount":0.45,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.63450292397661,"pricing":{"input":1.6500000000000001,"output":8.25,"cache_read":0.165,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"chutes","provider_display":"Chutes","quantization":"mxfp4","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":96.61016949152543,"pricing":{"input":1.85,"output":9.5,"cache_read":0.185,"cache_write":null},"org":"moonshot","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"moonshotai/Kimi-K3-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.5805535841022,"pricing":{"input":2.0999999999999996,"output":10.5,"cache_read":0.21,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/kimi-k3","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0.15,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.68701095461658,"pricing":{"input":2.5500000000000003,"output":12.75,"cache_read":0.255,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","logprobs","top_logprobs","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.5500000000000003,"output":12.95,"cache_read":0.255,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"kimi-k3","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"paretoalpha","provider_display":"ParetoAlpha","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","max_completion_tokens","parallel_tool_calls","response_format","structured_outputs","logprobs","top_logprobs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","top_k","stop","seed","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":97.07317073170731,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"moonshot","zdr":true,"modelsdev":{"base_url":null,"model_id":"us.moonshotai.kimi-k3","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"parasail","provider_display":"Parasail","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.73166368515206,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"modal","provider_display":"Modal","quantization":"mxfp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","stop","max_tokens","response_format","structured_outputs","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://inference.us-west.modal.direct/v1","model_id":"moonshotai/Kimi-K3","doc_url":"https://modal.com/docs/guide/endpoints","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.69696969696969,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":null,"model_id":"moonshotai/Kimi-K3","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"baseten","provider_display":"BaseTen","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"moonshotai/Kimi-K3","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"moonshot","provider_display":"Moonshot AI","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","structured_outputs","response_format","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3},"org":"moonshot","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.moonshot.ai/v1","model_id":"kimi-k3","doc_url":"https://platform.moonshot.ai/docs/api/chat","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","seed","presence_penalty","response_format","structured_outputs","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.97979797979798,"pricing":{"input":3.45,"output":17.25,"cache_read":0.345,"cache_write":null},"org":"moonshot","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"kimi-k3","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3:fast","name":"MoonshotAI: Kimi K3 (fast)","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":92.84467713787086,"pricing":{"input":4.5,"output":22.5,"cache_read":0.44999999999999996,"cache_write":null},"org":"moonshot","modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/kimi-k3","doc_url":"https://fireworks.ai/docs/","confidence":"medium","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k3:batch","name":"MoonshotAI: Kimi K3 (batch)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":1048576,"max_completion_tokens":16384,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","structured_outputs","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":2.2800000000000002,"output":11.399999999999999,"cache_read":0.228,"cache_write":3.5625},"org":"moonshot","modelsdev":{"base_url":null,"model_id":"moonshotai/Kimi-K3","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta/muse-spark-1.1","name":"Meta: Muse Spark 1.1","provider":"meta","provider_display":"Meta","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","repetition_penalty","top_k","temperature","top_p","tools","tool_choice","structured_outputs","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":null},"org":"meta","modelsdev":{"base_url":"https://api.meta.ai/v1","model_id":"muse-spark-1.1","doc_url":"https://dev.meta.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-04-08","knowledge_cutoff":null,"description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":71.3,"agentic_index":25.8,"design_arena_best":{"category":"uicomponent","elo":1282,"win_rate":50.9,"rank":25},"arena_text":1490.1758377985552,"arena_text_rank":13,"arena_text_rating_lower":1485.9299522977522,"arena_text_rating_upper":1494.4217232993585,"arena_text_vote_count":42810,"arena_text_date":"2026-10-15","arena_creative_writing":1443.6738692225429,"arena_creative_writing_rank":53,"arena_creative_writing_rating_lower":1436.3483038724455,"arena_creative_writing_rating_upper":1450.9994345726404,"arena_creative_writing_vote_count":8948,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-luna-pro:flex","name":"OpenAI: GPT-5.6 Luna Pro (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":0.09999999999999999,"output":0.6,"cache_read":0.01,"cache_write":0.125},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-luna-pro","name":"OpenAI: GPT-5.6 Luna Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1.2,"cache_read":0.02,"cache_write":0.25},"org":"openai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-luna-pro","name":"OpenAI: GPT-5.6 Luna Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1.2,"cache_read":0.02,"cache_write":0.25},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-luna-pro:fast","name":"OpenAI: GPT-5.6 Luna Pro (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":0.39999999999999997,"output":2.4,"cache_read":0.04,"cache_write":0.5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-luna-pro:batch","name":"OpenAI: GPT-5.6 Luna Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.09999999999999999,"output":0.6,"cache_read":0.01,"cache_write":null},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-luna:flex","name":"OpenAI: GPT-5.6 Luna (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":99.93055555555556,"pricing":{"input":0.09999999999999999,"output":0.6,"cache_read":0.01,"cache_write":0.125},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-luna","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":37.3,"coding_index":71.4,"agentic_index":42.1,"design_arena_best":null,"arena_text":1452.5662458726235,"arena_text_rank":75,"arena_text_rating_lower":1448.2646893469653,"arena_text_rating_upper":1456.8678023982818,"arena_text_vote_count":41109,"arena_text_date":"2026-10-15","arena_creative_writing":1409.8692518077291,"arena_creative_writing_rank":92,"arena_creative_writing_rating_lower":1402.2779905913478,"arena_creative_writing_rating_upper":1417.4605130241107,"arena_creative_writing_vote_count":8603,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1.2,"cache_read":0.02,"cache_write":0.25},"org":"openai","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5},{"above_tokens":272000,"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}],"modelsdev":{"base_url":null,"model_id":"gpt-5.6-luna","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":37.3,"coding_index":71.4,"agentic_index":42.1,"design_arena_best":null,"arena_text":1452.5662458726235,"arena_text_rank":75,"arena_text_rating_lower":1448.2646893469653,"arena_text_rating_upper":1456.8678023982818,"arena_text_vote_count":41109,"arena_text_date":"2026-10-15","arena_creative_writing":1409.8692518077291,"arena_creative_writing_rank":92,"arena_creative_writing_rating_lower":1402.2779905913478,"arena_creative_writing_rating_upper":1417.4605130241107,"arena_creative_writing_vote_count":8603,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1.2,"cache_read":0.02,"cache_write":0.25},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5},{"above_tokens":272000,"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}],"modelsdev":{"base_url":null,"model_id":"gpt-5.6-luna","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":37.3,"coding_index":71.4,"agentic_index":42.1,"design_arena_best":null,"arena_text":1452.5662458726235,"arena_text_rank":75,"arena_text_rating_lower":1448.2646893469653,"arena_text_rating_upper":1456.8678023982818,"arena_text_vote_count":41109,"arena_text_date":"2026-10-15","arena_creative_writing":1409.8692518077291,"arena_creative_writing_rank":92,"arena_creative_writing_rating_lower":1402.2779905913478,"arena_creative_writing_rating_upper":1417.4605130241107,"arena_creative_writing_vote_count":8603,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":99.85152190051967,"pricing":{"input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275},"org":"openai","modelsdev":{"base_url":null,"model_id":"openai.gpt-6-luna","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"medium","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-05-18","description":"OpenAI's most efficient model for focused, high-volume tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":37.3,"coding_index":71.4,"agentic_index":42.1,"design_arena_best":null,"arena_text":1452.5662458726235,"arena_text_rank":75,"arena_text_rating_lower":1448.2646893469653,"arena_text_rating_upper":1456.8678023982818,"arena_text_vote_count":41109,"arena_text_date":"2026-10-15","arena_creative_writing":1409.8692518077291,"arena_creative_writing_rank":92,"arena_creative_writing_rating_lower":1402.2779905913478,"arena_creative_writing_rating_upper":1417.4605130241107,"arena_creative_writing_vote_count":8603,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-luna:fast","name":"OpenAI: GPT-5.6 Luna (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":0.39999999999999997,"output":2.4,"cache_read":0.04,"cache_write":0.5},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-luna","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":37.3,"coding_index":71.4,"agentic_index":42.1,"design_arena_best":null,"arena_text":1452.5662458726235,"arena_text_rank":75,"arena_text_rating_lower":1448.2646893469653,"arena_text_rating_upper":1456.8678023982818,"arena_text_vote_count":41109,"arena_text_date":"2026-10-15","arena_creative_writing":1409.8692518077291,"arena_creative_writing_rank":92,"arena_creative_writing_rating_lower":1402.2779905913478,"arena_creative_writing_rating_upper":1417.4605130241107,"arena_creative_writing_vote_count":8603,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-luna:batch","name":"OpenAI: GPT-5.6 Luna (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":0.09999999999999999,"output":0.6,"cache_read":0.01,"cache_write":0.25},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-luna","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":37.3,"coding_index":71.4,"agentic_index":42.1,"design_arena_best":null,"arena_text":1452.5662458726235,"arena_text_rank":75,"arena_text_rating_lower":1448.2646893469653,"arena_text_rating_upper":1456.8678023982818,"arena_text_vote_count":41109,"arena_text_date":"2026-10-15","arena_creative_writing":1409.8692518077291,"arena_creative_writing_rank":92,"arena_creative_writing_rating_lower":1402.2779905913478,"arena_creative_writing_rating_upper":1417.4605130241107,"arena_creative_writing_vote_count":8603,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-terra-pro:flex","name":"OpenAI: GPT-5.6 Terra Pro (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":1,"output":6,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-terra-pro","name":"OpenAI: GPT-5.6 Terra Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":12,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-terra-pro","name":"OpenAI: GPT-5.6 Terra Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":12,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-terra-pro:fast","name":"OpenAI: GPT-5.6 Terra Pro (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":4,"output":24,"cache_read":0.39999999999999997,"cache_write":5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-terra-pro:batch","name":"OpenAI: GPT-5.6 Terra Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1,"output":6,"cache_read":0.09999999999999999,"cache_write":null},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-terra:flex","name":"OpenAI: GPT-5.6 Terra (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":98.84615384615385,"pricing":{"input":1,"output":6,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-terra","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":42.1,"coding_index":76.7,"agentic_index":43.2,"design_arena_best":null,"arena_text":1466.429395420974,"arena_text_rank":51,"arena_text_rating_lower":1462.172843173263,"arena_text_rating_upper":1470.685947668685,"arena_text_vote_count":43271,"arena_text_date":"2026-10-15","arena_creative_writing":1428.587050633098,"arena_creative_writing_rank":75,"arena_creative_writing_rating_lower":1421.1965094532784,"arena_creative_writing_rating_upper":1435.9775918129178,"arena_creative_writing_vote_count":9176,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":12,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":4,"output":18,"cache_read":0.4,"cache_write":5},{"above_tokens":272000,"input":4,"output":18,"cache_read":0.4,"cache_write":5}],"modelsdev":{"base_url":null,"model_id":"gpt-5.6-terra","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":42.1,"coding_index":76.7,"agentic_index":43.2,"design_arena_best":null,"arena_text":1466.429395420974,"arena_text_rank":51,"arena_text_rating_lower":1462.172843173263,"arena_text_rating_upper":1470.685947668685,"arena_text_vote_count":43271,"arena_text_date":"2026-10-15","arena_creative_writing":1428.587050633098,"arena_creative_writing_rank":75,"arena_creative_writing_rating_lower":1421.1965094532784,"arena_creative_writing_rating_upper":1435.9775918129178,"arena_creative_writing_vote_count":9176,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":12,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":4,"output":18,"cache_read":0.4,"cache_write":5},{"above_tokens":272000,"input":4,"output":18,"cache_read":0.4,"cache_write":5}],"modelsdev":{"base_url":null,"model_id":"gpt-5.6-terra","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":42.1,"coding_index":76.7,"agentic_index":43.2,"design_arena_best":null,"arena_text":1466.429395420974,"arena_text_rank":51,"arena_text_rating_lower":1462.172843173263,"arena_text_rating_upper":1470.685947668685,"arena_text_vote_count":43271,"arena_text_date":"2026-10-15","arena_creative_writing":1428.587050633098,"arena_creative_writing_rank":75,"arena_creative_writing_rating_lower":1421.1965094532784,"arena_creative_writing_rating_upper":1435.9775918129178,"arena_creative_writing_vote_count":9176,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":2.2,"output":13.200000000000001,"cache_read":0.22,"cache_write":2.75},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":42.1,"coding_index":76.7,"agentic_index":43.2,"design_arena_best":null,"arena_text":1466.429395420974,"arena_text_rank":51,"arena_text_rating_lower":1462.172843173263,"arena_text_rating_upper":1470.685947668685,"arena_text_vote_count":43271,"arena_text_date":"2026-10-15","arena_creative_writing":1428.587050633098,"arena_creative_writing_rank":75,"arena_creative_writing_rating_lower":1421.1965094532784,"arena_creative_writing_rating_upper":1435.9775918129178,"arena_creative_writing_vote_count":9176,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-terra:fast","name":"OpenAI: GPT-5.6 Terra (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":4,"output":24,"cache_read":0.39999999999999997,"cache_write":5},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-terra","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":42.1,"coding_index":76.7,"agentic_index":43.2,"design_arena_best":null,"arena_text":1466.429395420974,"arena_text_rank":51,"arena_text_rating_lower":1462.172843173263,"arena_text_rating_upper":1470.685947668685,"arena_text_vote_count":43271,"arena_text_date":"2026-10-15","arena_creative_writing":1428.587050633098,"arena_creative_writing_rank":75,"arena_creative_writing_rating_lower":1421.1965094532784,"arena_creative_writing_rating_upper":1435.9775918129178,"arena_creative_writing_vote_count":9176,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-terra:batch","name":"OpenAI: GPT-5.6 Terra (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":1,"output":6,"cache_read":0.09999999999999999,"cache_write":2.5},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-terra","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":42.1,"coding_index":76.7,"agentic_index":43.2,"design_arena_best":null,"arena_text":1466.429395420974,"arena_text_rank":51,"arena_text_rating_lower":1462.172843173263,"arena_text_rating_upper":1470.685947668685,"arena_text_vote_count":43271,"arena_text_date":"2026-10-15","arena_creative_writing":1428.587050633098,"arena_creative_writing_rank":75,"arena_creative_writing_rating_lower":1421.1965094532784,"arena_creative_writing_rating_upper":1435.9775918129178,"arena_creative_writing_vote_count":9176,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-sol-pro:flex","name":"OpenAI: GPT-5.6 Sol Pro (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-sol-pro","name":"OpenAI: GPT-5.6 Sol Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":4,"output":20,"cache_read":0.39999999999999997,"cache_write":5},"org":"openai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-sol-pro","name":"OpenAI: GPT-5.6 Sol Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":4,"output":20,"cache_read":0.39999999999999997,"cache_write":5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-sol-pro:fast","name":"OpenAI: GPT-5.6 Sol Pro (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":8,"output":40,"cache_read":0.7999999999999999,"cache_write":10},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-sol-pro:batch","name":"OpenAI: GPT-5.6 Sol Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.6-sol:flex","name":"OpenAI: GPT-5.6 Sol (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":78.3,"agentic_index":47.4,"design_arena_best":null,"arena_text":1484.7394950911005,"arena_text_rank":21,"arena_text_rating_lower":1480.4011455154182,"arena_text_rating_upper":1489.077844666783,"arena_text_vote_count":40442,"arena_text_date":"2026-10-15","arena_creative_writing":1468.63029595999,"arena_creative_writing_rank":20,"arena_creative_writing_rating_lower":1460.9860742346168,"arena_creative_writing_rating_upper":1476.2745176853632,"arena_creative_writing_vote_count":8408,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":4,"output":20,"cache_read":0.39999999999999997,"cache_write":5},"org":"openai","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":8,"output":30,"cache_read":0.8,"cache_write":10},{"above_tokens":272000,"input":8,"output":30,"cache_read":0.8,"cache_write":10}],"modelsdev":{"base_url":null,"model_id":"gpt-5.6-sol","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":78.3,"agentic_index":47.4,"design_arena_best":null,"arena_text":1484.7394950911005,"arena_text_rank":21,"arena_text_rating_lower":1480.4011455154182,"arena_text_rating_upper":1489.077844666783,"arena_text_vote_count":40442,"arena_text_date":"2026-10-15","arena_creative_writing":1468.63029595999,"arena_creative_writing_rank":20,"arena_creative_writing_rating_lower":1460.9860742346168,"arena_creative_writing_rating_upper":1476.2745176853632,"arena_creative_writing_vote_count":8408,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":4,"output":20,"cache_read":0.39999999999999997,"cache_write":5},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":8,"output":30,"cache_read":0.8,"cache_write":10},{"above_tokens":272000,"input":8,"output":30,"cache_read":0.8,"cache_write":10}],"modelsdev":{"base_url":null,"model_id":"gpt-5.6-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":78.3,"agentic_index":47.4,"design_arena_best":null,"arena_text":1484.7394950911005,"arena_text_rank":21,"arena_text_rating_lower":1480.4011455154182,"arena_text_rating_upper":1489.077844666783,"arena_text_vote_count":40442,"arena_text_date":"2026-10-15","arena_creative_writing":1468.63029595999,"arena_creative_writing_rank":20,"arena_creative_writing_rating_lower":1460.9860742346168,"arena_creative_writing_rating_upper":1476.2745176853632,"arena_creative_writing_vote_count":8408,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":4.4,"output":22,"cache_read":0.44,"cache_write":5.5},"org":"openai","modelsdev":{"base_url":null,"model_id":"global.openai.gpt-6-sol","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"medium","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-04-20","description":"OpenAI model for complex coding and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":78.3,"agentic_index":47.4,"design_arena_best":null,"arena_text":1484.7394950911005,"arena_text_rank":21,"arena_text_rating_lower":1480.4011455154182,"arena_text_rating_upper":1489.077844666783,"arena_text_vote_count":40442,"arena_text_date":"2026-10-15","arena_creative_writing":1468.63029595999,"arena_creative_writing_rank":20,"arena_creative_writing_rating_lower":1460.9860742346168,"arena_creative_writing_rating_upper":1476.2745176853632,"arena_creative_writing_vote_count":8408,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-sol:fast","name":"OpenAI: GPT-5.6 Sol (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":8,"output":40,"cache_read":0.7999999999999999,"cache_write":10},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":78.3,"agentic_index":47.4,"design_arena_best":null,"arena_text":1484.7394950911005,"arena_text_rank":21,"arena_text_rating_lower":1480.4011455154182,"arena_text_rating_upper":1489.077844666783,"arena_text_vote_count":40442,"arena_text_date":"2026-10-15","arena_creative_writing":1468.63029595999,"arena_creative_writing_rank":20,"arena_creative_writing_rating_lower":1460.9860742346168,"arena_creative_writing_rating_upper":1476.2745176853632,"arena_creative_writing_vote_count":8408,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.6-sol:batch","name":"OpenAI: GPT-5.6 Sol (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":78.3,"agentic_index":47.4,"design_arena_best":null,"arena_text":1484.7394950911005,"arena_text_rank":21,"arena_text_rating_lower":1480.4011455154182,"arena_text_rating_upper":1489.077844666783,"arena_text_vote_count":40442,"arena_text_date":"2026-10-15","arena_creative_writing":1468.63029595999,"arena_creative_writing_rank":20,"arena_creative_writing_rating_lower":1460.9860742346168,"arena_creative_writing_rating_upper":1476.2745176853632,"arena_creative_writing_vote_count":8408,"arena_creative_writing_date":"2026-10-15"}},{"id":"x-ai/grok-4.5","name":"SpaceXAI: Grok 4.5","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":500000,"max_completion_tokens":450000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":6,"cache_read":0.3,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"context_price_tiers":[{"above_tokens":200000,"input":4,"output":12,"cache_read":0.6,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"grok-4.5","doc_url":"https://docs.x.ai/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-08","knowledge_cutoff":null,"description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.8,"coding_index":72.4,"agentic_index":41.2,"design_arena_best":{"category":"website","elo":1280,"win_rate":52.4,"rank":25},"arena_text":1465.7091491137166,"arena_text_rank":52,"arena_text_rating_lower":1461.370929075886,"arena_text_rating_upper":1470.0473691515474,"arena_text_vote_count":39896,"arena_text_date":"2026-10-15","arena_creative_writing":1451.7173845789487,"arena_creative_writing_rank":36,"arena_creative_writing_rating_lower":1444.0718965383865,"arena_creative_writing_rating_upper":1459.3628726195107,"arena_creative_writing_vote_count":8298,"arena_creative_writing_date":"2026-10-15"}},{"id":"x-ai/grok-4.5:priority","name":"SpaceXAI: Grok 4.5 (priority)","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":500000,"max_completion_tokens":450000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":4,"output":12,"cache_read":0.6,"cache_write":null},"org":"xai","subscription":true,"modelsdev":{"base_url":null,"model_id":"grok-4.5","doc_url":"https://docs.x.ai/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-08","knowledge_cutoff":null,"description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.8,"coding_index":72.4,"agentic_index":41.2,"design_arena_best":{"category":"website","elo":1280,"win_rate":52.4,"rank":25},"arena_text":1465.7091491137166,"arena_text_rank":52,"arena_text_rating_lower":1461.370929075886,"arena_text_rating_upper":1470.0473691515474,"arena_text_vote_count":39896,"arena_text_date":"2026-10-15","arena_creative_writing":1451.7173845789487,"arena_creative_writing_rank":36,"arena_creative_writing_rating_lower":1444.0718965383865,"arena_creative_writing_rating_upper":1459.3628726195107,"arena_creative_writing_vote_count":8298,"arena_creative_writing_date":"2026-10-15"}},{"id":"aion-labs/aion-3.0-mini","name":"AionLabs: Aion-3.0-Mini","provider":"aionlabs","provider_display":"AionLabs","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7,"output":1.4,"cache_read":0.18,"cache_write":null},"org":"aion-labs","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"aion-labs/aion-3.0","name":"AionLabs: Aion-3.0","provider":"aionlabs","provider_display":"AionLabs","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.77997799779979,"pricing":{"input":3,"output":6,"cache_read":0.75,"cache_write":null},"org":"aion-labs","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"tencent/hy3","name":"Tencent: Hy3","provider":"tencent","provider_display":"Tencent","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","stop","max_completion_tokens","max_tokens","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":192000,"uptime_1d":100,"pricing":{"input":0.0825,"output":0.33,"cache_read":0.020625,"cache_write":0},"org":"tencent","zdr":true,"modelsdev":{"base_url":"https://tokenhub.tencentmaas.com/v1","model_id":"hy3","doc_url":"https://cloud.tencent.com/document/product/1823/130050","confidence":"high","source":"models.dev","release_date":"2026-07-06","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.3,"coding_index":58.8,"agentic_index":24.1,"design_arena_best":{"category":"website","elo":1180,"win_rate":41.3,"rank":76},"arena_text":1453.1921880349164,"arena_text_rank":74,"arena_text_rating_lower":1447.0448295263823,"arena_text_rating_upper":1459.3395465434508,"arena_text_vote_count":12208,"arena_text_date":"2026-10-15","arena_creative_writing":1421.8046324903116,"arena_creative_writing_rank":82,"arena_creative_writing_rating_lower":1409.2973161031023,"arena_creative_writing_rating_upper":1434.3119488775212,"arena_creative_writing_vote_count":2429,"arena_creative_writing_date":"2026-10-15"}},{"id":"tencent/hy3","name":"Tencent: Hy3","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":192000,"uptime_1d":100,"pricing":{"input":0.14,"output":0.58,"cache_read":0.035,"cache_write":null},"org":"tencent","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"tencent/hy3","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-07-06","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.3,"coding_index":58.8,"agentic_index":24.1,"design_arena_best":{"category":"website","elo":1180,"win_rate":41.3,"rank":76},"arena_text":1453.1921880349164,"arena_text_rank":74,"arena_text_rating_lower":1447.0448295263823,"arena_text_rating_upper":1459.3395465434508,"arena_text_vote_count":12208,"arena_text_date":"2026-10-15","arena_creative_writing":1421.8046324903116,"arena_creative_writing_rank":82,"arena_creative_writing_rating_lower":1409.2973161031023,"arena_creative_writing_rating_upper":1434.3119488775212,"arena_creative_writing_vote_count":2429,"arena_creative_writing_date":"2026-10-15"}},{"id":"tencent/hy3","name":"Tencent: Hy3","provider":"gmicloud","provider_display":"GMICloud","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.83471074380165,"pricing":{"input":0.14,"output":0.58,"cache_read":0.035,"cache_write":null},"org":"tencent","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-06","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.3,"coding_index":58.8,"agentic_index":24.1,"design_arena_best":{"category":"website","elo":1180,"win_rate":41.3,"rank":76},"arena_text":1453.1921880349164,"arena_text_rank":74,"arena_text_rating_lower":1447.0448295263823,"arena_text_rating_upper":1459.3395465434508,"arena_text_vote_count":12208,"arena_text_date":"2026-10-15","arena_creative_writing":1421.8046324903116,"arena_creative_writing_rank":82,"arena_creative_writing_rating_lower":1409.2973161031023,"arena_creative_writing_rating_upper":1434.3119488775212,"arena_creative_writing_vote_count":2429,"arena_creative_writing_date":"2026-10-15"}},{"id":"tencent/hy3","name":"Tencent: Hy3","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.83429991714996,"pricing":{"input":0.15,"output":0.64,"cache_read":0.04,"cache_write":null},"org":"tencent","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-06","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.3,"coding_index":58.8,"agentic_index":24.1,"design_arena_best":{"category":"website","elo":1180,"win_rate":41.3,"rank":76},"arena_text":1453.1921880349164,"arena_text_rank":74,"arena_text_rating_lower":1447.0448295263823,"arena_text_rating_upper":1459.3395465434508,"arena_text_vote_count":12208,"arena_text_date":"2026-10-15","arena_creative_writing":1421.8046324903116,"arena_creative_writing_rank":82,"arena_creative_writing_rating_lower":1409.2973161031023,"arena_creative_writing_rating_upper":1434.3119488775212,"arena_creative_writing_vote_count":2429,"arena_creative_writing_date":"2026-10-15"}},{"id":"tencent/hy3","name":"Tencent: Hy3","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.13559322033898,"pricing":{"input":0.19999999999999998,"output":0.7999999999999999,"cache_read":0.049999999999999996,"cache_write":null},"org":"tencent","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-06","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.3,"coding_index":58.8,"agentic_index":24.1,"design_arena_best":{"category":"website","elo":1180,"win_rate":41.3,"rank":76},"arena_text":1453.1921880349164,"arena_text_rank":74,"arena_text_rating_lower":1447.0448295263823,"arena_text_rating_upper":1459.3395465434508,"arena_text_vote_count":12208,"arena_text_date":"2026-10-15","arena_creative_writing":1421.8046324903116,"arena_creative_writing_rank":82,"arena_creative_writing_rating_lower":1409.2973161031023,"arena_creative_writing_rating_upper":1434.3119488775212,"arena_creative_writing_vote_count":2429,"arena_creative_writing_date":"2026-10-15"}},{"id":"poolside/laguna-xs-2.1","name":"Poolside: Laguna XS 2.1","provider":"poolside","provider_display":"Poolside","quantization":"fp8","discount":0.4,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.06,"output":0.12,"cache_read":0.03,"cache_write":0},"org":"poolside","modelsdev":{"base_url":"https://inference.poolside.ai/v1","model_id":"poolside/laguna-xs-2.1","doc_url":"https://platform.poolside.ai","confidence":"high","source":"models.dev","release_date":"2026-07-02","knowledge_cutoff":null,"description":"Agentic coding model from Poolside in the XS size class for local deployment","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-29","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.2,"coding_index":71.5,"agentic_index":43.6,"design_arena_best":{"category":"codecategories","elo":1274,"win_rate":52.5,"rank":28},"arena_text":1461.0744345634098,"arena_text_rank":58,"arena_text_rating_lower":1456.948350050117,"arena_text_rating_upper":1465.2005190767027,"arena_text_vote_count":49595,"arena_text_date":"2026-10-15","arena_creative_writing":1435.9673899026286,"arena_creative_writing_rank":64,"arena_creative_writing_rating_lower":1428.9376863536472,"arena_creative_writing_rating_upper":1442.99709345161,"arena_creative_writing_vote_count":10285,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-sonnet-5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-06-30","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.2,"coding_index":71.5,"agentic_index":43.6,"design_arena_best":{"category":"codecategories","elo":1274,"win_rate":52.5,"rank":28},"arena_text":1461.0744345634098,"arena_text_rank":58,"arena_text_rating_lower":1456.948350050117,"arena_text_rating_upper":1465.2005190767027,"arena_text_vote_count":49595,"arena_text_date":"2026-10-15","arena_creative_writing":1435.9673899026286,"arena_creative_writing_rank":64,"arena_creative_writing_rating_lower":1428.9376863536472,"arena_creative_writing_rating_upper":1442.99709345161,"arena_creative_writing_vote_count":10285,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","response_format","tools","tool_choice","verbosity","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-29","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.2,"coding_index":71.5,"agentic_index":43.6,"design_arena_best":{"category":"codecategories","elo":1274,"win_rate":52.5,"rank":28},"arena_text":1461.0744345634098,"arena_text_rank":58,"arena_text_rating_lower":1456.948350050117,"arena_text_rating_upper":1465.2005190767027,"arena_text_vote_count":49595,"arena_text_date":"2026-10-15","arena_creative_writing":1435.9673899026286,"arena_creative_writing_rank":64,"arena_creative_writing_rating_lower":1428.9376863536472,"arena_creative_writing_rating_upper":1442.99709345161,"arena_creative_writing_vote_count":10285,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tools","tool_choice","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","zdr":true,"modelsdev":{"base_url":null,"model_id":"eu.anthropic.claude-sonnet-5","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-06-30","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.2,"coding_index":71.5,"agentic_index":43.6,"design_arena_best":{"category":"codecategories","elo":1274,"win_rate":52.5,"rank":28},"arena_text":1461.0744345634098,"arena_text_rank":58,"arena_text_rating_lower":1456.948350050117,"arena_text_rating_upper":1465.2005190767027,"arena_text_vote_count":49595,"arena_text_date":"2026-10-15","arena_creative_writing":1435.9673899026286,"arena_creative_writing_rank":64,"arena_creative_writing_rating_lower":1428.9376863536472,"arena_creative_writing_rating_upper":1442.99709345161,"arena_creative_writing_vote_count":10285,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-sonnet-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"high","source":"models.dev","release_date":"2026-06-29","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.2,"coding_index":71.5,"agentic_index":43.6,"design_arena_best":{"category":"codecategories","elo":1274,"win_rate":52.5,"rank":28},"arena_text":1461.0744345634098,"arena_text_rank":58,"arena_text_rating_lower":1456.948350050117,"arena_text_rating_upper":1465.2005190767027,"arena_text_vote_count":49595,"arena_text_date":"2026-10-15","arena_creative_writing":1435.9673899026286,"arena_creative_writing_rank":64,"arena_creative_writing_rating_lower":1428.9376863536472,"arena_creative_writing_rating_upper":1442.99709345161,"arena_creative_writing_vote_count":10285,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-5:batch","name":"Anthropic: Claude Sonnet 5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-sonnet-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"medium","source":"models.dev","release_date":"2026-06-29","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.2,"coding_index":71.5,"agentic_index":43.6,"design_arena_best":{"category":"codecategories","elo":1274,"win_rate":52.5,"rank":28},"arena_text":1461.0744345634098,"arena_text_rank":58,"arena_text_rating_lower":1456.948350050117,"arena_text_rating_upper":1465.2005190767027,"arena_text_vote_count":49595,"arena_text_date":"2026-10-15","arena_creative_writing":1435.9673899026286,"arena_creative_writing_rank":64,"arena_creative_writing_rating_lower":1428.9376863536472,"arena_creative_writing_rating_upper":1442.99709345161,"arena_creative_writing_vote_count":10285,"arena_creative_writing_date":"2026-10-15"}},{"id":"sakana/fugu-ultra","name":"Sakana: Fugu Ultra","provider":"sakana","provider_display":"Sakana AI","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","structured_outputs","web_search_options","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"sakana","context_price_tiers":[{"above_tokens":200000,"input":10,"output":45,"cache_read":1,"cache_write":null},{"above_tokens":272000,"input":10,"output":45,"cache_read":1,"cache_write":null}],"modelsdev":{"base_url":"https://api.sakana.ai/v1","model_id":"fugu-ultra","doc_url":"https://console.sakana.ai/models","confidence":"high","source":"models.dev","release_date":"2026-06-15","knowledge_cutoff":null,"description":"Quality-first multi-agent model for hard research, analysis, and competitions","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"relace","provider_display":"Relace","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.83948635634029,"pricing":{"input":0.006500000000000001,"output":7.9056999999999995,"cache_read":0.006500000000000001,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"morph","provider_display":"Morph","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.89462048636699,"pricing":{"input":0.176,"output":1.544,"cache_read":0.06899999999999999,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","tools","structured_outputs","response_format","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.19,"output":8,"cache_read":0.19,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/zai-org/glm-5.2","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2:flex","name":"Z.ai: GLM 5.2 (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0.25,"context_length":1048576,"max_completion_tokens":163840,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.44999999999999996,"output":1.44,"cache_read":0.08399999999999999,"cache_write":0.9375},"org":"z-ai","modelsdev":{"base_url":null,"model_id":"zai-org/GLM-5.2","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"ambient","provider_display":"Ambient","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":182476,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","top_p","response_format","structured_outputs","tools","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.30917874396135,"pricing":{"input":0.6,"output":2,"cache_read":0.15,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.563,"context_length":1024000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","tool_choice","tools","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6118,"output":1.9228,"cache_read":0.11362,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2:fast","name":"Z.ai: GLM 5.2 (fast)","provider":"baidu","provider_display":"Baidu","quantization":"fp4","discount":0.725,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","repetition_penalty","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.61875,"output":2.1670000000000003,"cache_read":0.154,"cache_write":null},"org":"z-ai","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.558,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","repetition_penalty","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6188,"output":1.9448,"cache_read":0.11492,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","tools","logprobs","top_logprobs","structured_outputs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.62,"output":2.42,"cache_read":0.14,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.536,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6496,"output":2.0416,"cache_read":0.12064,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-5.2","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","tool_choice","tools","response_format","logprobs","top_logprobs","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.89878542510121,"pricing":{"input":0.7,"output":2.2,"cache_read":0.105,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"glm-5.2","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0.5,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7,"output":2.2,"cache_read":0.13,"cache_write":0},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"zai-org/GLM-5.2","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0.33,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.938,"output":2.948,"cache_read":0.17420000000000002,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":1048576,"uptime_1d":100,"pricing":{"input":0.966,"output":3.036,"cache_read":0.1932,"cache_write":0},"org":"z-ai","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"glm-5.2","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"inceptron","provider_display":"Inceptron","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","stop","frequency_penalty","logit_bias","parallel_tool_calls","presence_penalty","seed","response_format","logprobs","top_logprobs","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.2,"output":4.4,"cache_read":0.16,"cache_write":0},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.inceptron.io/v1","model_id":"zai-org/GLM-5.2","doc_url":"https://docs.inceptron.io","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2 (fast)","provider":"decart","provider_display":"Decart","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.2,"output":8,"cache_read":0.48,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"nebius","provider_display":"Nebius","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":33.33333333333333,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":72.00902934537245,"pricing":{"input":1.4,"output":4.4,"cache_read":0.14,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"zai-org/GLM-5.2","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"mistral","provider_display":"Mistral","quantization":"nvfp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.79166666666667,"pricing":{"input":1.4,"output":4.4,"cache_read":0.14,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"baseten","provider_display":"BaseTen","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.14,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"zai-org/GLM-5.2","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1048575,"max_completion_tokens":943717,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.71870604781998,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"zai-org/GLM-5.2","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","structured_outputs","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"zai-org/GLM-5.2-FP8","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"medium","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"parasail","provider_display":"Parasail","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.91319444444444,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"friendli","provider_display":"Friendli","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.friendli.ai/serverless/v1","model_id":"zai-org/GLM-5.2","doc_url":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5.2","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2:fast","name":"Z.ai: GLM 5.2 (fast)","provider":"baseten","provider_display":"BaseTen","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.0999999999999996,"output":6.6000000000000005,"cache_read":0.21,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"zai-org/GLM-5.2","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"medium","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.2:fast","name":"Z.ai: GLM 5.2 (fast)","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":1048576,"uptime_1d":100,"pricing":{"input":2.31,"output":7.26,"cache_read":0.46199999999999997,"cache_write":0},"org":"z-ai","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"glm-5.2","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"medium","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"inceptron","provider_display":"Inceptron","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","stop","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","frequency_penalty","logit_bias","parallel_tool_calls","presence_penalty","seed"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.86091794158554,"pricing":{"input":0.56,"output":3.1,"cache_read":0.15,"cache_write":0},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.inceptron.io/v1","model_id":"moonshotai/Kimi-K2.7-Code","doc_url":"https://docs.inceptron.io","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"coreweave","provider_display":"CoreWeave","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6,"output":3,"cache_read":0.12,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0.25,"context_length":256000,"max_completion_tokens":32000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","top_p","stop","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.24242424242425,"pricing":{"input":0.7124999999999999,"output":3,"cache_read":0.14250000000000002,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"venice","provider_display":"Venice","quantization":"int4","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","response_format","structured_outputs","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.27007299270073,"pricing":{"input":0.75,"output":3.5,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.85916,"output":3.8,"cache_read":0.17993,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"moonshotai/Kimi-K2.7-Code","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"novita","provider_display":"Novita","quantization":"int4","discount":0.04,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.912,"output":3.84,"cache_read":0.18239999999999998,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"moonshotai/kimi-k2.7-code","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"nebius","provider_display":"Nebius","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","logprobs","top_logprobs","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":96.68874172185431,"pricing":{"input":0.95,"output":4,"cache_read":0.15,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"moonshotai/Kimi-K2.7-Code","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"moonshot","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"moonshotai/kimi-k2.7-code-highspeed","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"medium","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","structured_outputs","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":229376,"uptime_1d":100,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"moonshot","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/moonshotai/kimi-k2.7-code","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"moonshot","provider_display":"Moonshot AI","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","structured_outputs","response_format","tool_choice","tools","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"moonshot","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.moonshot.ai/v1","model_id":"kimi-k2.7-code","doc_url":"https://platform.moonshot.ai/docs/api/chat","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"moonshotai/kimi-k2.7-code:highspeed","name":"MoonshotAI: Kimi K2.7 Code (highspeed)","provider":"moonshot","provider_display":"Moonshot AI","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","tools","response_format","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.9,"output":8,"cache_read":0.38,"cache_write":null},"org":"moonshot","subscription":true,"modelsdev":{"base_url":"https://api.moonshot.ai/v1","model_id":"kimi-k2.7-code","doc_url":"https://platform.moonshot.ai/docs/api/chat","confidence":"medium","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-07","knowledge_cutoff":null,"description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.6,"coding_index":76.5,"agentic_index":50.7,"design_arena_best":{"category":"gamedev","elo":1335,"win_rate":60.8,"rank":11},"arena_text":1503.6013443401307,"arena_text_rank":4,"arena_text_rating_lower":1499.3137424347174,"arena_text_rating_upper":1507.888946245544,"arena_text_vote_count":42004,"arena_text_date":"2026-10-15","arena_creative_writing":1501.3084222192924,"arena_creative_writing_rank":3,"arena_creative_writing_rating_lower":1493.9313686628855,"arena_creative_writing_rating_upper":1508.6854757756996,"arena_creative_writing_vote_count":9020,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","lifecycle_status":"beta","modelsdev":{"base_url":null,"model_id":"claude-fable-5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-06-09","knowledge_cutoff":"2026-01-31","description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":49.6,"coding_index":76.5,"agentic_index":50.7,"design_arena_best":{"category":"gamedev","elo":1335,"win_rate":60.8,"rank":11},"arena_text":1503.6013443401307,"arena_text_rank":4,"arena_text_rating_lower":1499.3137424347174,"arena_text_rating_upper":1507.888946245544,"arena_text_vote_count":42004,"arena_text_date":"2026-10-15","arena_creative_writing":1501.3084222192924,"arena_creative_writing_rank":3,"arena_creative_writing_rating_lower":1493.9313686628855,"arena_creative_writing_rating_upper":1508.6854757756996,"arena_creative_writing_vote_count":9020,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"eu.anthropic.claude-fable-5","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-06-09","knowledge_cutoff":"2026-01-31","description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.6,"coding_index":76.5,"agentic_index":50.7,"design_arena_best":{"category":"gamedev","elo":1335,"win_rate":60.8,"rank":11},"arena_text":1503.6013443401307,"arena_text_rank":4,"arena_text_rating_lower":1499.3137424347174,"arena_text_rating_upper":1507.888946245544,"arena_text_vote_count":42004,"arena_text_date":"2026-10-15","arena_creative_writing":1501.3084222192924,"arena_creative_writing_rank":3,"arena_creative_writing_rating_lower":1493.9313686628855,"arena_creative_writing_rating_upper":1508.6854757756996,"arena_creative_writing_vote_count":9020,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","response_format","tool_choice","tools","verbosity","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-07","knowledge_cutoff":null,"description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.6,"coding_index":76.5,"agentic_index":50.7,"design_arena_best":{"category":"gamedev","elo":1335,"win_rate":60.8,"rank":11},"arena_text":1503.6013443401307,"arena_text_rank":4,"arena_text_rating_lower":1499.3137424347174,"arena_text_rating_upper":1507.888946245544,"arena_text_vote_count":42004,"arena_text_date":"2026-10-15","arena_creative_writing":1501.3084222192924,"arena_creative_writing_rank":3,"arena_creative_writing_rating_lower":1493.9313686628855,"arena_creative_writing_rating_upper":1508.6854757756996,"arena_creative_writing_vote_count":9020,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-fable-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"high","source":"models.dev","release_date":"2026-06-07","knowledge_cutoff":null,"description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.6,"coding_index":76.5,"agentic_index":50.7,"design_arena_best":{"category":"gamedev","elo":1335,"win_rate":60.8,"rank":11},"arena_text":1503.6013443401307,"arena_text_rank":4,"arena_text_rating_lower":1499.3137424347174,"arena_text_rating_upper":1507.888946245544,"arena_text_vote_count":42004,"arena_text_date":"2026-10-15","arena_creative_writing":1501.3084222192924,"arena_creative_writing_rank":3,"arena_creative_writing_rating_lower":1493.9313686628855,"arena_creative_writing_rating_upper":1508.6854757756996,"arena_creative_writing_vote_count":9020,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-fable-5:batch","name":"Anthropic: Claude Fable 5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-fable-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"medium","source":"models.dev","release_date":"2026-06-07","knowledge_cutoff":null,"description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":49.6,"coding_index":76.5,"agentic_index":50.7,"design_arena_best":{"category":"gamedev","elo":1335,"win_rate":60.8,"rank":11},"arena_text":1503.6013443401307,"arena_text_rank":4,"arena_text_rating_lower":1499.3137424347174,"arena_text_rating_upper":1507.888946245544,"arena_text_vote_count":42004,"arena_text_date":"2026-10-15","arena_creative_writing":1501.3084222192924,"arena_creative_writing_rank":3,"arena_creative_writing_rating_lower":1493.9313686628855,"arena_creative_writing_rating_upper":1508.6854757756996,"arena_creative_writing_vote_count":9020,"arena_creative_writing_date":"2026-10-15"}},{"id":"nvidia/nemotron-3.5-content-safety","name":"NVIDIA: Nemotron 3.5 Content Safety","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"nvidia","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"nvidia/nemotron-3-ultra-550b-a55b:flex","name":"NVIDIA: Nemotron 3 Ultra (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.39999999999999997,"output":1.76,"cache_read":0.08,"cache_write":null},"org":"nvidia","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.8,"coding_index":49.3,"agentic_index":20.1,"design_arena_best":{"category":"codecategories","elo":1146,"win_rate":36,"rank":89}}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","structured_outputs","response_format","logit_bias","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.5,"output":2.2,"cache_read":0.09999999999999999,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-04","knowledge_cutoff":"2025-09","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.tokenfactory.nebius.com/","reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.8,"coding_index":49.3,"agentic_index":20.1,"design_arena_best":{"category":"codecategories","elo":1146,"win_rate":36,"rank":89}}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","provider":"baseten","provider_display":"BaseTen","quantization":"fp4","discount":0,"context_length":202800,"max_completion_tokens":182520,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6,"output":2.4,"cache_read":0.12,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"medium","source":"models.dev","release_date":"2026-06-04","knowledge_cutoff":"2025-09","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.8,"coding_index":49.3,"agentic_index":20.1,"design_arena_best":{"category":"codecategories","elo":1146,"win_rate":36,"rank":89}}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.625,"output":3.125,"cache_read":0.1875,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev":{"base_url":null,"model_id":"nvidia-nemotron-3-ultra-550b-a55b","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2026-06-04","knowledge_cutoff":"2025-09","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.8,"coding_index":49.3,"agentic_index":20.1,"design_arena_best":{"category":"codecategories","elo":1146,"win_rate":36,"rank":89}}},{"id":"qwen/qwen3.7-plus","name":"Qwen: Qwen3.7 Plus","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","logprobs","top_logprobs","tools","tool_choice","structured_outputs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":983616,"uptime_1d":100,"pricing":{"input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0.39999999999999997},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.7-plus","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-06-02","knowledge_cutoff":"2025-04","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.2,"coding_index":55.9,"agentic_index":17.5,"design_arena_best":{"category":"dataviz","elo":1279,"win_rate":51.3,"rank":22},"arena_text":1455.682715060256,"arena_text_rank":69,"arena_text_rating_lower":1451.3500504663698,"arena_text_rating_upper":1460.0153796541422,"arena_text_vote_count":42075,"arena_text_date":"2026-10-15","arena_creative_writing":1431.499455939465,"arena_creative_writing_rank":72,"arena_creative_writing_rating_lower":1423.8736889483803,"arena_creative_writing_rating_upper":1439.1252229305496,"arena_creative_writing_vote_count":7841,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.7-plus:batch","name":"Qwen: Qwen3.7 Plus (batch)","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","logprobs","top_logprobs","tools","tool_choice","structured_outputs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":245760,"uptime_1d":null,"pricing":{"input":0.22999999999999998,"output":0.9199999999999999,"cache_read":0.08,"cache_write":0.5},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.7-plus","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"medium","source":"models.dev","release_date":"2026-06-02","knowledge_cutoff":"2025-04","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.2,"coding_index":55.9,"agentic_index":17.5,"design_arena_best":{"category":"dataviz","elo":1279,"win_rate":51.3,"rank":22},"arena_text":1455.682715060256,"arena_text_rank":69,"arena_text_rating_lower":1451.3500504663698,"arena_text_rating_upper":1460.0153796541422,"arena_text_vote_count":42075,"arena_text_date":"2026-10-15","arena_creative_writing":1431.499455939465,"arena_creative_writing_rank":72,"arena_creative_writing_rating_lower":1423.8736889483803,"arena_creative_writing_rating_upper":1439.1252229305496,"arena_creative_writing_vote_count":7841,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3:flex","name":"MiniMax: MiniMax M3 (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":524288,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":87.36141906873614,"pricing":{"input":0.224,"output":0.88,"cache_read":0.0448,"cache_write":null},"org":"minimax","modelsdev":{"base_url":null,"model_id":"MiniMaxAI/MiniMax-M3","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-06-01","knowledge_cutoff":null,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.92997198879551,"pricing":{"input":0.22999999999999998,"output":0.96,"cache_read":0.049999999999999996,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-01","knowledge_cutoff":null,"description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.2,"context_length":1048576,"max_completion_tokens":524288,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.58982772764561,"pricing":{"input":0.24,"output":0.96,"cache_read":0.048,"cache_write":null},"org":"minimax","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"MiniMaxAI/MiniMax-M3","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"high","source":"models.dev","release_date":"2026-06-01","knowledge_cutoff":null,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.5,"context_length":1000000,"max_completion_tokens":512000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","max_tokens","temperature","top_p","stop","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.26948051948052,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-01","knowledge_cutoff":null,"description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":524288,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.24496644295301,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":null,"model_id":"minimax-m3-preview","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":524288,"max_completion_tokens":471859,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.92912827781714,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":null,"model_id":"MiniMaxAI/MiniMax-M3","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-06-01","knowledge_cutoff":null,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":524288,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":false,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.78401727861771,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-01","knowledge_cutoff":null,"description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":524300,"max_completion_tokens":524288,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.83498349834984,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-01","knowledge_cutoff":null,"description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":0.6,"output":2.4,"cache_read":0.12,"cache_write":null},{"above_tokens":524288,"input":0.6,"output":2.4,"cache_read":0.12,"cache_write":null}],"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"minimax/minimax-m3","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-06-01","knowledge_cutoff":null,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":524288,"max_completion_tokens":512000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tool_choice","tools"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":524288,"uptime_1d":99.93050729673384,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-01","knowledge_cutoff":null,"description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"modelrun","provider_display":"ModelRun","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","presence_penalty","repetition_penalty","frequency_penalty","top_p","top_k","stop","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.3,"cache_read":0.049999999999999996,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-01","knowledge_cutoff":null,"description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"mara","provider_display":"Mara","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_k","top_p","response_format","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6,"output":2.4,"cache_read":null,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-01","knowledge_cutoff":null,"description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://fireworks.ai/docs/","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"stepfun/step-3.7-flash","name":"StepFun: Step 3.7 Flash","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":256000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":256000,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1.15,"cache_read":0.04,"cache_write":null},"org":"stepfun","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"stepfun/step-3.7-flash","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-05-29","knowledge_cutoff":"2026-03-01","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":19.5,"coding_index":39.6,"agentic_index":null,"design_arena_best":{"category":"website","elo":1195,"win_rate":43.9,"rank":66}}},{"id":"stepfun/step-3.7-flash","name":"StepFun: Step 3.7 Flash","provider":"stepfun","provider_display":"StepFun","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":230400,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","tools","top_p","stop","frequency_penalty","logprobs","top_logprobs","response_format","structured_outputs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":256000,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1.15,"cache_read":0.04,"cache_write":null},"org":"stepfun","modelsdev":{"base_url":"https://api.stepfun.com/v1","model_id":"step-3.7-flash","doc_url":"https://platform.stepfun.com/docs/zh/overview/concept","confidence":"high","source":"models.dev","release_date":"2026-05-29","knowledge_cutoff":"2026-03-01","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":19.5,"coding_index":39.6,"agentic_index":null,"design_arena_best":{"category":"website","elo":1195,"win_rate":43.9,"rank":66}}},{"id":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-28","knowledge_cutoff":"2026-01","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":74.3,"agentic_index":41.9,"design_arena_best":{"category":"agenticslides(python-pptx)","elo":1310,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-28","knowledge_cutoff":"2026-01","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":74.3,"agentic_index":41.9,"design_arena_best":{"category":"agenticslides(python-pptx)","elo":1310,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":74.3,"agentic_index":41.9,"design_arena_best":{"category":"agenticslides(python-pptx)","elo":1310,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","response_format","tool_choice","tools","verbosity","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-28","knowledge_cutoff":"2026-01","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":74.3,"agentic_index":41.9,"design_arena_best":{"category":"agenticslides(python-pptx)","elo":1310,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-28","knowledge_cutoff":"2026-01","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":74.3,"agentic_index":41.9,"design_arena_best":{"category":"agenticslides(python-pptx)","elo":1310,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-4.8:fast","name":"Anthropic: Claude Opus 4.8 (fast)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":74.3,"agentic_index":41.9,"design_arena_best":{"category":"agenticslides(python-pptx)","elo":1310,"win_rate":68.9,"rank":1}}},{"id":"anthropic/claude-opus-4.8:batch","name":"Anthropic: Claude Opus 4.8 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":74.3,"agentic_index":41.9,"design_arena_best":{"category":"agenticslides(python-pptx)","elo":1310,"win_rate":68.9,"rank":1}}},{"id":"qwen/qwen3.7-max","name":"Qwen: Qwen3.7 Max","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":983616,"uptime_1d":100,"pricing":{"input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.7-max","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-05-21","knowledge_cutoff":null,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.5,"coding_index":66,"agentic_index":22.5,"design_arena_best":{"category":"dataviz","elo":1276,"win_rate":53,"rank":24},"arena_text":1474.346453572102,"arena_text_rank":39,"arena_text_rating_lower":1464.6199672413577,"arena_text_rating_upper":1484.0729399028464,"arena_text_vote_count":3934,"arena_text_date":"2026-10-15","arena_creative_writing":1439.2456129096304,"arena_creative_writing_rank":60,"arena_creative_writing_rating_lower":1411.9628845744933,"arena_creative_writing_rating_upper":1466.5283412447675,"arena_creative_writing_vote_count":508,"arena_creative_writing_date":"2026-10-15"}},{"id":"x-ai/grok-build-0.1","name":"SpaceXAI: Grok Build 0.1","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":230400,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":2,"cache_read":0.19999999999999998,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"context_price_tiers":[{"above_tokens":200000,"input":2,"output":4,"cache_read":0.4,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"grok-build-0.1","doc_url":"https://docs.x.ai/docs/models","confidence":"high","source":"models.dev","release_date":"2026-04-16","knowledge_cutoff":null,"description":"Fast Grok coding model tuned for agentic engineering and iterative edits","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":51.5,"agentic_index":null,"design_arena_best":null}},{"id":"x-ai/grok-build-0.1:priority","name":"SpaceXAI: Grok Build 0.1 (priority)","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":230400,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":4,"cache_read":0.39999999999999997,"cache_write":null},"org":"xai","subscription":true,"modelsdev":{"base_url":null,"model_id":"grok-build-0.1","doc_url":"https://docs.x.ai/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-04-16","knowledge_cutoff":null,"description":"Fast Grok coding model tuned for agentic engineering and iterative edits","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":51.5,"agentic_index":null,"design_arena_best":null}},{"id":"google/gemini-3.5-flash:flex","name":"Google: Gemini 3.5 Flash (flex)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":84.61538461538461,"pricing":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.0416666666666667},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-05-19","knowledge_cutoff":"2025-01","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":32.6,"coding_index":70.1,"agentic_index":26,"design_arena_best":{"category":"uicomponent","elo":1267,"win_rate":54.1,"rank":32}}},{"id":"google/gemini-3.5-flash","name":"Google: Gemini 3.5 Flash","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.0833333333333333},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-05-19","knowledge_cutoff":"2025-01","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":32.6,"coding_index":70.1,"agentic_index":26,"design_arena_best":{"category":"uicomponent","elo":1267,"win_rate":54.1,"rank":32}}},{"id":"google/gemini-3.5-flash:priority","name":"Google: Gemini 3.5 Flash (priority)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.7,"output":16.2,"cache_read":0.27,"cache_write":0.15},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-05-19","knowledge_cutoff":"2025-01","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":32.6,"coding_index":70.1,"agentic_index":26,"design_arena_best":{"category":"uicomponent","elo":1267,"win_rate":54.1,"rank":32}}},{"id":"google/gemini-3.5-flash:batch","name":"Google: Gemini 3.5 Flash (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":null},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-05-19","knowledge_cutoff":"2025-01","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":32.6,"coding_index":70.1,"agentic_index":26,"design_arena_best":{"category":"uicomponent","elo":1267,"win_rate":54.1,"rank":32}}},{"id":"perceptron/perceptron-mk1","name":"Perceptron: Perceptron Mk1","provider":"perceptron","provider_display":"Perceptron","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.80544747081711,"pricing":{"input":0.15,"output":1.5,"cache_read":null,"cache_write":null},"org":"perceptron","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"google/gemini-3.1-flash-lite:flex","name":"Google: Gemini 3.1 Flash Lite (flex)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":64,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":67.36621196222455,"pricing":{"input":0.125,"output":0.75,"cache_read":0.012499999999999999,"cache_write":0.0416666666666667},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.1-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-05-07","knowledge_cutoff":"2025-01","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":15.6,"coding_index":34.7,"agentic_index":1.6,"design_arena_best":{"category":"asciiart","elo":1164,"win_rate":50.8,"rank":33},"arena_text":1432.9270943558301,"arena_text_rank":110,"arena_text_rating_lower":1429.3054802422857,"arena_text_rating_upper":1436.5487084693743,"arena_text_vote_count":64211,"arena_text_date":"2026-10-15","arena_creative_writing":1414.317968777435,"arena_creative_writing_rank":89,"arena_creative_writing_rating_lower":1407.4610934144926,"arena_creative_writing_rating_upper":1421.1748441403774,"arena_creative_writing_vote_count":10600,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.1-flash-lite","name":"Google: Gemini 3.1 Flash Lite","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.25,"output":1.5,"cache_read":0.024999999999999998,"cache_write":0.0833333333333333},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3.1-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-05-07","knowledge_cutoff":"2025-01","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":15.6,"coding_index":34.7,"agentic_index":1.6,"design_arena_best":{"category":"asciiart","elo":1164,"win_rate":50.8,"rank":33},"arena_text":1432.9270943558301,"arena_text_rank":110,"arena_text_rating_lower":1429.3054802422857,"arena_text_rating_upper":1436.5487084693743,"arena_text_vote_count":64211,"arena_text_date":"2026-10-15","arena_creative_writing":1414.317968777435,"arena_creative_writing_rank":89,"arena_creative_writing_rating_lower":1407.4610934144926,"arena_creative_writing_rating_upper":1421.1748441403774,"arena_creative_writing_vote_count":10600,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.1-flash-lite:priority","name":"Google: Gemini 3.1 Flash Lite (priority)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.44999999999999996,"output":2.7,"cache_read":0.045,"cache_write":0.15},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.1-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-05-07","knowledge_cutoff":"2025-01","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":15.6,"coding_index":34.7,"agentic_index":1.6,"design_arena_best":{"category":"asciiart","elo":1164,"win_rate":50.8,"rank":33},"arena_text":1432.9270943558301,"arena_text_rank":110,"arena_text_rating_lower":1429.3054802422857,"arena_text_rating_upper":1436.5487084693743,"arena_text_vote_count":64211,"arena_text_date":"2026-10-15","arena_creative_writing":1414.317968777435,"arena_creative_writing_rank":89,"arena_creative_writing_rating_lower":1407.4610934144926,"arena_creative_writing_rating_upper":1421.1748441403774,"arena_creative_writing_vote_count":10600,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.1-flash-lite:batch","name":"Google: Gemini 3.1 Flash Lite (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","stop","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.125,"output":0.75,"cache_read":0.012499999999999999,"cache_write":null},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.1-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-05-07","knowledge_cutoff":"2025-01","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":15.6,"coding_index":34.7,"agentic_index":1.6,"design_arena_best":{"category":"asciiart","elo":1164,"win_rate":50.8,"rank":33},"arena_text":1432.9270943558301,"arena_text_rank":110,"arena_text_rating_lower":1429.3054802422857,"arena_text_rating_upper":1436.5487084693743,"arena_text_vote_count":64211,"arena_text_date":"2026-10-15","arena_creative_writing":1414.317968777435,"arena_creative_writing_rank":89,"arena_creative_writing_rating_lower":1407.4610934144926,"arena_creative_writing_rating_upper":1421.1748441403774,"arena_creative_writing_vote_count":10600,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-chat-latest","name":"OpenAI: GPT Chat Latest","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"openai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-05","knowledge_cutoff":"2025-12-01","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[{"type":"effort","values":["medium"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"x-ai/grok-4.3","name":"SpaceXAI: Grok 4.3","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":900000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":95.82753824756607,"pricing":{"input":1.25,"output":2.5,"cache_read":0.19999999999999998,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"context_price_tiers":[{"above_tokens":200000,"input":2.5,"output":5,"cache_read":0.4,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"grok-4.3","doc_url":"https://docs.x.ai/docs/models","confidence":"high","source":"models.dev","release_date":"2026-04-17","knowledge_cutoff":null,"description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.9,"coding_index":42.2,"agentic_index":15.5,"design_arena_best":{"category":"website","elo":1195,"win_rate":44,"rank":65},"arena_text":1441.7179508681295,"arena_text_rank":93,"arena_text_rating_lower":1438.0914375496773,"arena_text_rating_upper":1445.3444641865815,"arena_text_vote_count":71347,"arena_text_date":"2026-10-15","arena_creative_writing":1422.2034026938807,"arena_creative_writing_rank":81,"arena_creative_writing_rating_lower":1415.7069743233883,"arena_creative_writing_rating_upper":1428.699831064373,"arena_creative_writing_vote_count":13226,"arena_creative_writing_date":"2026-10-15"}},{"id":"x-ai/grok-4.3:priority","name":"SpaceXAI: Grok 4.3 (priority)","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":900000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.5,"output":5,"cache_read":0.39999999999999997,"cache_write":null},"org":"xai","subscription":true,"modelsdev":{"base_url":null,"model_id":"grok-4.3","doc_url":"https://docs.x.ai/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-04-17","knowledge_cutoff":null,"description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.9,"coding_index":42.2,"agentic_index":15.5,"design_arena_best":{"category":"website","elo":1195,"win_rate":44,"rank":65},"arena_text":1441.7179508681295,"arena_text_rank":93,"arena_text_rating_lower":1438.0914375496773,"arena_text_rating_upper":1445.3444641865815,"arena_text_vote_count":71347,"arena_text_date":"2026-10-15","arena_creative_writing":1422.2034026938807,"arena_creative_writing_rank":81,"arena_creative_writing_rating_lower":1415.7069743233883,"arena_creative_writing_rating_upper":1428.699831064373,"arena_creative_writing_vote_count":13226,"arena_creative_writing_date":"2026-10-15"}},{"id":"x-ai/grok-4.3:batch","name":"SpaceXAI: Grok 4.3 (batch)","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":900000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1,"output":2,"cache_read":0.16,"cache_write":null},"org":"xai","subscription":true,"modelsdev":{"base_url":null,"model_id":"grok-4.3","doc_url":"https://docs.x.ai/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-04-17","knowledge_cutoff":null,"description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.9,"coding_index":42.2,"agentic_index":15.5,"design_arena_best":{"category":"website","elo":1195,"win_rate":44,"rank":65},"arena_text":1441.7179508681295,"arena_text_rank":93,"arena_text_rating_lower":1438.0914375496773,"arena_text_rating_upper":1445.3444641865815,"arena_text_vote_count":71347,"arena_text_date":"2026-10-15","arena_creative_writing":1422.2034026938807,"arena_creative_writing_rank":81,"arena_creative_writing_rating_lower":1415.7069743233883,"arena_creative_writing_rating_upper":1428.699831064373,"arena_creative_writing_vote_count":13226,"arena_creative_writing_date":"2026-10-15"}},{"id":"mistralai/mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":209715,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":98.71279163314561,"pricing":{"input":1.5,"output":7.5,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":46.9,"agentic_index":7,"design_arena_best":null}},{"id":"mistralai/mistral-medium-3-5:batch","name":"Mistral: Mistral Medium 3.5 (batch)","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":209715,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.75,"output":3.75,"cache_read":null,"cache_write":null},"org":"mistral","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":46.9,"agentic_index":7,"design_arena_best":null}},{"id":"qwen/qwen3.5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":983616,"uptime_1d":100,"pricing":{"input":0.3,"output":1.7999999999999998,"cache_read":null,"cache_write":0.375},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.5-plus","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-02-16","knowledge_cutoff":"2025-04","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3.6-flash","name":"Qwen: Qwen3.6 Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":983616,"uptime_1d":100,"pricing":{"input":0.1875,"output":1.125,"cache_read":0.025,"cache_write":0.234375},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.6-flash","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-04-27","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"darkbloom","provider_display":"Darkbloom","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":96,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.68627450980392,"pricing":{"input":0.049999999999999996,"output":0.7,"cache_read":0.024999999999999998,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"akashml","provider_display":"AkashML","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","repetition_penalty","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.8999999999999999,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.8999999999999999,"cache_read":0.024999999999999998,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.95,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"dekallm","provider_display":"DekaLLM","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logit_bias","max_tokens","presence_penalty","seed","stop","temperature","top_p","tools","tool_choice","logprobs","top_logprobs","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":1,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":95.65217391304348,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.30167597765363,"pricing":{"input":0.09999999999999999,"output":1,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","structured_outputs","tools","logprobs","top_logprobs","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.30139720558883,"pricing":{"input":0.19999999999999998,"output":1.27,"cache_read":0.056,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.24,"output":1.7999999999999998,"cache_read":0.15,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3.6-35B-A3B","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.25,"output":1.25,"cache_read":0.25,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.2,"coding_index":41.9,"agentic_index":13.1,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"reka","provider_display":"Reka","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":50,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","max_tokens","stop","seed","frequency_penalty","presence_penalty","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":96.88888888888889,"pricing":{"input":0.19999999999999998,"output":3,"cache_read":0.19999999999999998,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":21.4,"coding_index":53.7,"agentic_index":18.5,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"chutes","provider_display":"Chutes","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":78.26086956521739,"pricing":{"input":0.25,"output":2,"cache_read":0.024999999999999998,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"Qwen/Qwen3.6-27B-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":21.4,"coding_index":53.7,"agentic_index":18.5,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":80.42704626334519,"pricing":{"input":0.3,"output":3.1999999999999997,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3.6-27B","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":21.4,"coding_index":53.7,"agentic_index":18.5,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262140,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":93.53448275862068,"pricing":{"input":0.32,"output":3.25,"cache_read":0.03,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":21.4,"coding_index":53.7,"agentic_index":18.5,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tool_choice","tools","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.75144987572494,"pricing":{"input":0.325,"output":3.25,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":21.4,"coding_index":53.7,"agentic_index":18.5,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_logprobs","logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":258048,"uptime_1d":99.81684981684981,"pricing":{"input":0.44999999999999996,"output":2.7,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.6-27b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":21.4,"coding_index":53.7,"agentic_index":18.5,"design_arena_best":null}},{"id":"openai/gpt-5.5-pro:flex","name":"OpenAI: GPT-5.5 Pro (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":15,"output":90,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.5-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-04-23","knowledge_cutoff":"2025-12-01","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.5-pro","name":"OpenAI: GPT-5.5 Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":30,"output":180,"cache_read":null,"cache_write":null},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":60,"output":270,"cache_read":null,"cache_write":null},{"above_tokens":272000,"input":60,"output":270,"cache_read":null,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"gpt-5.5-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-04-23","knowledge_cutoff":"2025-12-01","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null},{"id":"openai/gpt-5.5-pro:batch","name":"OpenAI: GPT-5.5 Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":15,"output":90,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.5-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-04-23","knowledge_cutoff":"2025-12-01","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.5:flex","name":"OpenAI: GPT-5.5 (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.5","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-04-23","knowledge_cutoff":"2025-12-01","description":"Default frontier GPT for coding, computer use, research, and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.4,"coding_index":74.9,"agentic_index":36.4,"design_arena_best":{"category":"gamedev","elo":1292,"win_rate":56.6,"rank":21},"arena_text":1476.6721977017742,"arena_text_rank":31,"arena_text_rating_lower":1472.9844992886817,"arena_text_rating_upper":1480.3598961148664,"arena_text_vote_count":70985,"arena_text_date":"2026-10-15","arena_creative_writing":1448.1066993336644,"arena_creative_writing_rank":41,"arena_creative_writing_rating_lower":1441.5574458384926,"arena_creative_writing_rating_upper":1454.655952828836,"arena_creative_writing_vote_count":13402,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.5","name":"OpenAI: GPT-5.5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"openai","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":10,"output":45,"cache_read":1,"cache_write":null},{"above_tokens":272000,"input":10,"output":45,"cache_read":1,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"gpt-5.5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-12-01","description":"Default frontier GPT for coding, computer use, research, and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.4,"coding_index":74.9,"agentic_index":36.4,"design_arena_best":{"category":"gamedev","elo":1292,"win_rate":56.6,"rank":21},"arena_text":1476.6721977017742,"arena_text_rank":31,"arena_text_rating_lower":1472.9844992886817,"arena_text_rating_upper":1480.3598961148664,"arena_text_vote_count":70985,"arena_text_date":"2026-10-15","arena_creative_writing":1448.1066993336644,"arena_creative_writing_rank":41,"arena_creative_writing_rating_lower":1441.5574458384926,"arena_creative_writing_rating_upper":1454.655952828836,"arena_creative_writing_vote_count":13402,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.5","name":"OpenAI: GPT-5.5","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":10,"output":45,"cache_read":1,"cache_write":null},{"above_tokens":272000,"input":10,"output":45,"cache_read":1,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"gpt-5.5","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-04-23","knowledge_cutoff":"2025-12-01","description":"Default frontier GPT for coding, computer use, research, and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.4,"coding_index":74.9,"agentic_index":36.4,"design_arena_best":{"category":"gamedev","elo":1292,"win_rate":56.6,"rank":21},"arena_text":1476.6721977017742,"arena_text_rank":31,"arena_text_rating_lower":1472.9844992886817,"arena_text_rating_upper":1480.3598961148664,"arena_text_vote_count":70985,"arena_text_date":"2026-10-15","arena_creative_writing":1448.1066993336644,"arena_creative_writing_rank":41,"arena_creative_writing_rating_lower":1441.5574458384926,"arena_creative_writing_rating_upper":1454.655952828836,"arena_creative_writing_vote_count":13402,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.5","name":"OpenAI: GPT-5.5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":5.5,"output":33,"cache_read":0.55,"cache_write":null},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.4,"coding_index":74.9,"agentic_index":36.4,"design_arena_best":{"category":"gamedev","elo":1292,"win_rate":56.6,"rank":21},"arena_text":1476.6721977017742,"arena_text_rank":31,"arena_text_rating_lower":1472.9844992886817,"arena_text_rating_upper":1480.3598961148664,"arena_text_vote_count":70985,"arena_text_date":"2026-10-15","arena_creative_writing":1448.1066993336644,"arena_creative_writing_rank":41,"arena_creative_writing_rating_lower":1441.5574458384926,"arena_creative_writing_rating_upper":1454.655952828836,"arena_creative_writing_vote_count":13402,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.5:fast","name":"OpenAI: GPT-5.5 (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":12.5,"output":75,"cache_read":1.25,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.5","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-04-23","knowledge_cutoff":"2025-12-01","description":"Default frontier GPT for coding, computer use, research, and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.4,"coding_index":74.9,"agentic_index":36.4,"design_arena_best":{"category":"gamedev","elo":1292,"win_rate":56.6,"rank":21},"arena_text":1476.6721977017742,"arena_text_rank":31,"arena_text_rating_lower":1472.9844992886817,"arena_text_rating_upper":1480.3598961148664,"arena_text_vote_count":70985,"arena_text_date":"2026-10-15","arena_creative_writing":1448.1066993336644,"arena_creative_writing_rank":41,"arena_creative_writing_rating_lower":1441.5574458384926,"arena_creative_writing_rating_upper":1454.655952828836,"arena_creative_writing_vote_count":13402,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.5:batch","name":"OpenAI: GPT-5.5 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.5","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-04-23","knowledge_cutoff":"2025-12-01","description":"Default frontier GPT for coding, computer use, research, and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":38.4,"coding_index":74.9,"agentic_index":36.4,"design_arena_best":{"category":"gamedev","elo":1292,"win_rate":56.6,"rank":21},"arena_text":1476.6721977017742,"arena_text_rank":31,"arena_text_rating_lower":1472.9844992886817,"arena_text_rating_upper":1480.3598961148664,"arena_text_vote_count":70985,"arena_text_date":"2026-10-15","arena_creative_writing":1448.1066993336644,"arena_creative_writing_rank":41,"arena_creative_writing_rating_lower":1441.5574458384926,"arena_creative_writing_rating_upper":1454.655952828836,"arena_creative_writing_vote_count":13402,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.5144,"context_length":1024000,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","response_format","logprobs","top_logprobs","structured_outputs","max_tokens","temperature","top_p","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.844944,"output":1.689888,"cache_read":0.070412,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.499,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.84669,"output":1.69338,"cache_read":0.07014000000000001,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"relace","provider_display":"Relace","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","stop","max_tokens","logit_bias","frequency_penalty","presence_penalty","repetition_penalty","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.8999999999999999,"output":1.5,"cache_read":0.25,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.45,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.9569999999999999,"output":1.9139999999999997,"cache_read":0.07975,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"deepseek-ai/DeepSeek-V4-Pro","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.79094076655052,"pricing":{"input":1,"output":3.1350000000000002,"cache_read":0.135,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"deepseek-ai/DeepSeek-V4-Pro","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","tool_choice","tools","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.044,"output":2.088,"cache_read":0.20879999999999999,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"deepseek-v4-pro","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.85422740524781,"pricing":{"input":1.15,"output":2.5500000000000003,"cache_read":0.19999999999999998,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/deepseek-ai/deepseek-v4-pro-0813","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"medium","source":"models.dev","release_date":"2026-08-13","knowledge_cutoff":null,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","structured_outputs","top_k","frequency_penalty","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":1000000,"uptime_1d":97.61668321747766,"pricing":{"input":1.4160000000000001,"output":2.8320000000000003,"cache_read":0.118,"cache_write":null},"org":"deepseek","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":1.5999999999999999,"output":3.1999999999999997,"cache_read":0.135,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-v4-pro","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.644128113879,"pricing":{"input":1.6500000000000001,"output":3.3009999999999997,"cache_read":0.33,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-v4-pro","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","tools","structured_outputs","response_format","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.36601307189542,"pricing":{"input":1.68,"output":3.38,"cache_read":0.13,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"crusoe","provider_display":"Crusoe","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.32914375490967,"pricing":{"input":1.74,"output":3.48,"cache_read":0.15,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.929676511955,"pricing":{"input":1.91,"output":3.8299999999999996,"cache_read":0.16,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-v4-pro","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"relace","provider_display":"Relace","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","stop","max_tokens","logit_bias","frequency_penalty","presence_penalty","repetition_penalty","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.044899999999999995,"output":0.44999999999999996,"cache_read":0.044899999999999995,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.662,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":94.09722222222221,"pricing":{"input":0.04732,"output":0.09464,"cache_read":0.009464,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.5,"context_length":1024000,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","tools","tool_choice","logprobs","top_logprobs","structured_outputs","max_tokens","temperature","top_p","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.07,"output":0.14,"cache_read":0.014,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.35,"context_length":1048575,"max_completion_tokens":943717,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.091,"output":0.182,"cache_read":0.0182,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"deepseek-ai/DeepSeek-V4-Flash","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0.3,"context_length":1000000,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.30555555555556,"pricing":{"input":0.0966,"output":0.1925,"cache_read":0.0196,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-v4-flash","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","tool_choice","tools","structured_outputs","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.098,"output":0.196,"cache_read":0.0196,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"deepseek-v4-flash-0731","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"medium","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":79.3103448275862,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","logprobs","top_logprobs","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":73.54330708661418,"pricing":{"input":0.105,"output":0.21,"cache_read":0.020999999999999998,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.86111111111111,"pricing":{"input":0.13,"output":0.28,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"deepseek-ai/DeepSeek-V4-Flash","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"crusoe","provider_display":"Crusoe","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.14,"output":0.28,"cache_read":0.03,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":false,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.26388888888889,"pricing":{"input":0.14,"output":0.28,"cache_read":0.028,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","structured_outputs","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.30555555555556,"pricing":{"input":0.14,"output":0.28,"cache_read":0.07,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":393216,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","structured_outputs","top_k","frequency_penalty","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":1000000,"uptime_1d":89.44444444444444,"pricing":{"input":0.15,"output":0.3,"cache_read":0.03,"cache_write":null},"org":"deepseek","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"deepseek-v4-flash-0731","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"medium","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","response_format","logprobs","top_logprobs","tools","structured_outputs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.67320261437908,"pricing":{"input":0.19,"output":0.5,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.79123173277662,"pricing":{"input":0.21,"output":0.56,"cache_read":0.031,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-v4-flash","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":384000,"max_completion_tokens":345600,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.44,"output":1.32,"cache_read":0.014,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/deepseek-ai/deepseek-v4-flash-0731","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"medium","source":"models.dev","release_date":"2026-07-31","knowledge_cutoff":"2025-05","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"wafer","provider_display":"Wafer","quantization":"mxfp4","discount":0,"context_length":1048576,"max_completion_tokens":943718,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6,"output":0.16999999999999998,"cache_read":0.19999999999999998,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","provider":"gmicloud","provider_display":"GMICloud","quantization":"bf16","discount":0.3,"context_length":1050000,"max_completion_tokens":945000,"uptime_30m":0,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format"],"supports_tool_choice":false,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":0,"pricing":{"input":0.3045,"output":0.609,"cache_read":0.0028,"cache_write":null},"org":"xiaomi","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26,"coding_index":60.2,"agentic_index":21.3,"design_arena_best":{"category":"codecategories","elo":1266,"win_rate":51.7,"rank":35},"arena_text":1467.2561325712447,"arena_text_rank":49,"arena_text_rating_lower":1463.7152451466172,"arena_text_rating_upper":1470.7970199958725,"arena_text_vote_count":75721,"arena_text_date":"2026-10-15","arena_creative_writing":1433.903257618414,"arena_creative_writing_rank":67,"arena_creative_writing_rating_lower":1427.7056499079981,"arena_creative_writing_rating_upper":1440.10086532883,"arena_creative_writing_vote_count":14122,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":1024000,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"supports_tool_choice":false,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":94.46009389671362,"pricing":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":null},"org":"xiaomi","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26,"coding_index":60.2,"agentic_index":21.3,"design_arena_best":{"category":"codecategories","elo":1266,"win_rate":51.7,"rank":35},"arena_text":1467.2561325712447,"arena_text_rank":49,"arena_text_rating_lower":1463.7152451466172,"arena_text_rating_upper":1470.7970199958725,"arena_text_vote_count":75721,"arena_text_date":"2026-10-15","arena_creative_writing":1433.903257618414,"arena_creative_writing_rank":67,"arena_creative_writing_rating_lower":1427.7056499079981,"arena_creative_writing_rating_upper":1440.10086532883,"arena_creative_writing_vote_count":14122,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.36111111111111,"pricing":{"input":0.48,"output":1.7999999999999998,"cache_read":0.096,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"mimo-v2.5-pro","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26,"coding_index":60.2,"agentic_index":21.3,"design_arena_best":{"category":"codecategories","elo":1266,"win_rate":51.7,"rank":35},"arena_text":1467.2561325712447,"arena_text_rank":49,"arena_text_rating_lower":1463.7152451466172,"arena_text_rating_upper":1470.7970199958725,"arena_text_vote_count":75721,"arena_text_date":"2026-10-15","arena_creative_writing":1433.903257618414,"arena_creative_writing_rank":67,"arena_creative_writing_rating_lower":1427.7056499079981,"arena_creative_writing_rating_upper":1440.10086532883,"arena_creative_writing_vote_count":14122,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.15,"context_length":1050000,"max_completion_tokens":945000,"uptime_30m":0,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":false,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":0,"pricing":{"input":0.119,"output":0.238,"cache_read":0.00255,"cache_write":null},"org":"xiaomi","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"Open MiMo model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.8,"agentic_index":15.8,"design_arena_best":{"category":"website","elo":1265,"win_rate":53.6,"rank":35},"arena_text":1433.780160902417,"arena_text_rank":108,"arena_text_rating_lower":1429.557633161148,"arena_text_rating_upper":1438.002688643686,"arena_text_vote_count":47362,"arena_text_date":"2026-10-15","arena_creative_writing":1394.990883226929,"arena_creative_writing_rank":116,"arena_creative_writing_rating_lower":1387.2259701258565,"arena_creative_writing_rating_upper":1402.7557963280017,"arena_creative_writing_vote_count":7900,"arena_creative_writing_date":"2026-10-15"}},{"id":"xiaomi/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":90.41666666666667,"pricing":{"input":0.39999999999999997,"output":2,"cache_read":0.08,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"Open MiMo model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.8,"agentic_index":15.8,"design_arena_best":{"category":"website","elo":1265,"win_rate":53.6,"rank":35},"arena_text":1433.780160902417,"arena_text_rank":108,"arena_text_rating_lower":1429.557633161148,"arena_text_rating_upper":1438.002688643686,"arena_text_vote_count":47362,"arena_text_date":"2026-10-15","arena_creative_writing":1394.990883226929,"arena_creative_writing_rank":116,"arena_creative_writing_rating_lower":1387.2259701258565,"arena_creative_writing_rating_upper":1402.7557963280017,"arena_creative_writing_vote_count":7900,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"baidu","provider_display":"Baidu","quantization":"fp4","discount":0.59,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","stop","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.62935507783544,"pricing":{"input":0.3895,"output":1.64,"cache_read":0.0656,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"chutes","provider_display":"Chutes","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":65535,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.30875576036865,"pricing":{"input":0.39,"output":1.7999999999999998,"cache_read":0.039,"cache_write":null},"org":"moonshot","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"moonshotai/Kimi-K2.6-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","structured_outputs","response_format","tool_choice","tools","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.87515605493134,"pricing":{"input":0.5700000000000001,"output":2.4,"cache_read":0.114,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"kimi-k2.6","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.37,"context_length":256000,"max_completion_tokens":230400,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","stop","top_p","temperature","max_tokens","tool_choice","tools","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":95.07042253521126,"pricing":{"input":0.5984999999999999,"output":2.52,"cache_read":0.1008,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"inceptron","provider_display":"Inceptron","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","max_tokens","top_p","stop","frequency_penalty","logit_bias","parallel_tool_calls","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6236,"output":3.5,"cache_read":0.1674,"cache_write":0},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.inceptron.io/v1","model_id":"moonshotai/Kimi-K2.6","doc_url":"https://docs.inceptron.io","confidence":"high","source":"models.dev","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.01418439716312,"pricing":{"input":0.65,"output":3.41,"cache_read":0.15,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"crusoe","provider_display":"Crusoe","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.18049490538574,"pricing":{"input":0.7,"output":3.5,"cache_read":0.35,"cache_write":null},"org":"moonshot","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":"https://api.inference.crusoecloud.com/v1","model_id":"moonshotai/Kimi-K2.6","doc_url":"https://docs.crusoecloud.com/managed-inference/overview","confidence":"high","source":"models.dev","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"venice","provider_display":"Venice","quantization":"int4","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tool_choice","tools","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":95.58823529411765,"pricing":{"input":0.75,"output":3.5,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"parasail","provider_display":"Parasail","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.92810927390366,"pricing":{"input":0.75,"output":3.5,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","response_format","tools","tool_choice","structured_outputs","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.77,"output":3.4,"cache_read":0.14,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"moonshotai/Kimi-K2.6","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7999999999999999,"output":3.4,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"moonshotai/kimi-k2.6","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.1,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":0,"pricing":{"input":0.855,"output":3.5999999999999996,"cache_read":0.144,"cache_write":null},"org":"moonshot","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"moonshotai/Kimi-K2.6","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"high","source":"models.dev","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","tool_choice","tools","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.70689655172413,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","min_p","stop","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/moonshotai/kimi-k2.6","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"moonshot","provider_display":"Moonshot AI","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","structured_outputs","response_format","tool_choice","tools","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.77876106194691,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.moonshot.ai/v1","model_id":"kimi-k2.6","doc_url":"https://platform.moonshot.ai/docs/api/chat","confidence":"high","source":"models.dev","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","structured_outputs","response_format","tool_choice","tools"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.0899999999999999,"output":4.6,"cache_read":0.37,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27,"coding_index":61.8,"agentic_index":20.5,"design_arena_best":{"category":"spreadsheet","elo":1276,"win_rate":54.8,"rank":8},"arena_text":1460.8290167351456,"arena_text_rank":59,"arena_text_rating_lower":1456.4017956312816,"arena_text_rating_upper":1465.2562378390096,"arena_text_vote_count":40013,"arena_text_date":"2026-10-15","arena_creative_writing":1432.2857550603376,"arena_creative_writing_rank":71,"arena_creative_writing_rating_lower":1424.0692876132543,"arena_creative_writing_rating_upper":1440.5022225074208,"arena_creative_writing_vote_count":6317,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-16","knowledge_cutoff":"2026-01-31","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":73.6,"agentic_index":38.6,"design_arena_best":null,"arena_text":1493.5865745597428,"arena_text_rank":11,"arena_text_rating_lower":1489.8257265063335,"arena_text_rating_upper":1497.3474226131518,"arena_text_vote_count":66216,"arena_text_date":"2026-10-15","arena_creative_writing":1482.4296665567133,"arena_creative_writing_rank":11,"arena_creative_writing_rating_lower":1475.575644005423,"arena_creative_writing_rating_upper":1489.2836891080037,"arena_creative_writing_vote_count":12033,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","max_completion_tokens","tools","tool_choice","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-16","knowledge_cutoff":"2026-01-31","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":73.6,"agentic_index":38.6,"design_arena_best":null,"arena_text":1493.5865745597428,"arena_text_rank":11,"arena_text_rating_lower":1489.8257265063335,"arena_text_rating_upper":1497.3474226131518,"arena_text_vote_count":66216,"arena_text_date":"2026-10-15","arena_creative_writing":1482.4296665567133,"arena_creative_writing_rank":11,"arena_creative_writing_rating_lower":1475.575644005423,"arena_creative_writing_rating_upper":1489.2836891080037,"arena_creative_writing_vote_count":12033,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","response_format","tool_choice","tools","verbosity","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-16","knowledge_cutoff":"2026-01-31","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":73.6,"agentic_index":38.6,"design_arena_best":null,"arena_text":1493.5865745597428,"arena_text_rank":11,"arena_text_rating_lower":1489.8257265063335,"arena_text_rating_upper":1497.3474226131518,"arena_text_vote_count":66216,"arena_text_date":"2026-10-15","arena_creative_writing":1482.4296665567133,"arena_creative_writing_rank":11,"arena_creative_writing_rating_lower":1475.575644005423,"arena_creative_writing_rating_upper":1489.2836891080037,"arena_creative_writing_vote_count":12033,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.79166666666667,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":73.6,"agentic_index":38.6,"design_arena_best":null,"arena_text":1493.5865745597428,"arena_text_rank":11,"arena_text_rating_lower":1489.8257265063335,"arena_text_rating_upper":1497.3474226131518,"arena_text_vote_count":66216,"arena_text_date":"2026-10-15","arena_creative_writing":1482.4296665567133,"arena_creative_writing_rank":11,"arena_creative_writing_rating_lower":1475.575644005423,"arena_creative_writing_rating_upper":1489.2836891080037,"arena_creative_writing_vote_count":12033,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-16","knowledge_cutoff":"2026-01-31","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":73.6,"agentic_index":38.6,"design_arena_best":null,"arena_text":1493.5865745597428,"arena_text_rank":11,"arena_text_rating_lower":1489.8257265063335,"arena_text_rating_upper":1497.3474226131518,"arena_text_vote_count":66216,"arena_text_date":"2026-10-15","arena_creative_writing":1482.4296665567133,"arena_creative_writing_rank":11,"arena_creative_writing_rating_lower":1475.575644005423,"arena_creative_writing_rating_upper":1489.2836891080037,"arena_creative_writing_vote_count":12033,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.7:batch","name":"Anthropic: Claude Opus 4.7 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":73.6,"agentic_index":38.6,"design_arena_best":null,"arena_text":1493.5865745597428,"arena_text_rank":11,"arena_text_rating_lower":1489.8257265063335,"arena_text_rating_upper":1497.3474226131518,"arena_text_vote_count":66216,"arena_text_date":"2026-10-15","arena_creative_writing":1482.4296665567133,"arena_creative_writing_rank":11,"arena_creative_writing_rating_lower":1475.575644005423,"arena_creative_writing_rating_upper":1489.2836891080037,"arena_creative_writing_vote_count":12033,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"chutes","provider_display":"Chutes","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":65535,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","structured_outputs","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.73591549295774,"pricing":{"input":0.8999999999999999,"output":2.9000000000000004,"cache_read":0.09,"cache_write":null},"org":"z-ai","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"zai-org/GLM-5.1-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.31,"context_length":200000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.966,"output":3.036,"cache_read":0.1794,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.8529411764706,"pricing":{"input":1.19,"output":3.74,"cache_read":0.6,"cache_write":0},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"zai-org/GLM-5.1","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":202752,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","tool_choice","tools","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.21,"output":4.199999999999999,"cache_read":0.6,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":182476,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.26,"output":3.9600000000000004,"cache_read":0.234,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":202745,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","structured_outputs","tools","logprobs","top_logprobs","top_k","frequency_penalty","stop","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":169984,"uptime_1d":100,"pricing":{"input":1.33,"output":4.18,"cache_read":0.24699999999999997,"cache_write":null},"org":"z-ai","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.38,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-5.1","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":182476,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.74597798475868,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","frequency_penalty","presence_penalty","repetition_penalty","stop","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":182476,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"zai-org/GLM-5.1-FP8","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"medium","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"friendli","provider_display":"Friendli","quantization":"unknown","discount":0,"context_length":202752,"max_completion_tokens":182476,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.friendli.ai/serverless/v1","model_id":"zai-org/GLM-5.1","doc_url":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.57537154989384,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5.1","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0.09,"context_length":200000,"max_completion_tokens":80000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.4014,"output":4.4044,"cache_read":0.26026,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.1,"coding_index":55.8,"agentic_index":23.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3},"arena_text":1465.1654788552419,"arena_text_rank":54,"arena_text_rating_lower":1461.580487104311,"arena_text_rating_upper":1468.7504706061725,"arena_text_vote_count":62889,"arena_text_date":"2026-10-15","arena_creative_writing":1447.067416330387,"arena_creative_writing_rank":43,"arena_creative_writing_rating_lower":1440.65268335141,"arena_creative_writing_rating_upper":1453.482149309364,"arena_creative_writing_vote_count":12259,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"darkbloom","provider_display":"Darkbloom","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.79152189020152,"pricing":{"input":0.041999999999999996,"output":0.22,"cache_read":0.020999999999999998,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 26B A4B is a multimodal MoE model with LoRA support and function calling for agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"dekallm","provider_display":"DekaLLM","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logit_bias","max_tokens","presence_penalty","seed","stop","temperature","top_p","tools","tool_choice","logprobs","top_logprobs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.06,"output":0.33,"cache_read":0.04,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 26B A4B is a multimodal MoE model with LoRA support and function calling for agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"akashml","provider_display":"AkashML","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","repetition_penalty","seed","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.07,"output":0.24,"cache_read":0.046,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 26B A4B is a multimodal MoE model with LoRA support and function calling for agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"makora","provider_display":"Makora","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","max_tokens","seed","response_format","tools","tool_choice","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.07,"output":0.24,"cache_read":0.046,"cache_write":null},"org":"google","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 26B A4B is a multimodal MoE model with LoRA support and function calling for agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"nextbit","provider_display":"NextBit","quantization":"bf16","discount":0.15,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.0765,"output":0.255,"cache_read":0.042499999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 26B A4B is a multimodal MoE model with LoRA support and function calling for agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"io-net","provider_display":"Io Net","quantization":"bf16","discount":0,"context_length":262142,"max_completion_tokens":235927,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","tools","logprobs","top_logprobs","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09,"output":0.31,"cache_read":0.041,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 26B A4B is a multimodal MoE model with LoRA support and function calling for agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"primeintellect","provider_display":"PrimeIntellect","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","min_p","presence_penalty","repetition_penalty","max_tokens","max_completion_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 26B A4B is a multimodal MoE model with LoRA support and function calling for agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"coreweave","provider_display":"CoreWeave","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.049999999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 26B A4B is a multimodal MoE model with LoRA support and function calling for agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":230400,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.049999999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/google/gemma-4-26b-a4b-it","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"venice","provider_display":"Venice","quantization":"bf16","discount":0,"context_length":256000,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.13,"output":0.39999999999999997,"cache_read":0.049999999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"google-gemma-4-26b-a4b-it","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.13,"output":0.39999999999999997,"cache_read":0.049999999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 26B A4B is a multimodal MoE model with LoRA support and function calling for agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.13,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"google/gemma-4-26b-a4b-it","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":93.69715603382014,"pricing":{"input":0.14,"output":0.39999999999999997,"cache_read":0.049999999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"google/gemma-4-26B-A4B-it","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":93.33333333333333,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","tools","tool_choice","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":91.75334323922733,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemma-4-26b-a4b-it","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":39.3,"agentic_index":2.9,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.33999999999999997,"cache_read":0.09999999999999999,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"venice","provider_display":"Venice","quantization":"fp4","discount":0,"context_length":256000,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.12,"output":0.36,"cache_read":0.09,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"google-gemma-4-31b-it","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"chutes","provider_display":"Chutes","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.59825327510917,"pricing":{"input":0.12,"output":0.37,"cache_read":0.012,"cache_write":null},"org":"google","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it:turbo","name":"Google: Gemma 4 31B (turbo)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","structured_outputs","logit_bias","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.135,"output":0.51,"cache_read":0.075,"cache_write":null},"org":"google","modelsdev":{"base_url":null,"model_id":"google/gemma-4-31B-it","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"dekallm","provider_display":"DekaLLM","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logit_bias","max_tokens","presence_penalty","seed","stop","temperature","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.91796554552911,"pricing":{"input":0.14,"output":0.39999999999999997,"cache_read":0.049999999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"crusoe","provider_display":"Crusoe","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":262141,"uptime_30m":96.66666666666667,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.23558026407228,"pricing":{"input":0.14,"output":0.39999999999999997,"cache_read":0.14,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":"https://api.inference.crusoecloud.com/v1","model_id":"google/gemma-4-31b-it","doc_url":"https://docs.crusoecloud.com/managed-inference/overview","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"friendli","provider_display":"Friendli","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.09722222222223,"pricing":{"input":0.14,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"google","modelsdev":{"base_url":"https://api.friendli.ai/serverless/v1","model_id":"google/gemma-4-31B-it","doc_url":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":87.56944444444444,"pricing":{"input":0.14,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"google/gemma-4-31b-it","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.78494623655914,"pricing":{"input":0.15,"output":0.39999999999999997,"cache_read":0.06,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it:flex","name":"Google: Gemma 4 31B (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.16,"output":0.32,"cache_read":null,"cache_write":null},"org":"google","modelsdev":{"base_url":null,"model_id":"google/gemma-4-31B-it","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it:priority","name":"Google: Gemma 4 31B (priority)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.35111751982696,"pricing":{"input":0.3,"output":0.6,"cache_read":null,"cache_write":null},"org":"google","modelsdev":{"base_url":null,"model_id":"google/gemma-4-31B-it","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"io-net","provider_display":"Io Net","quantization":"unknown","discount":0.05,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","response_format","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.36100000000000004,"output":1.0925,"cache_read":0.18050000000000002,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"modelrun","provider_display":"ModelRun","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","presence_penalty","repetition_penalty","frequency_penalty","top_p","top_k","stop","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.75,"output":1,"cache_read":0.19999999999999998,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":93.33333333333333,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","max_tokens","response_format","structured_outputs","tool_choice","tools"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.27095990279466,"pricing":{"input":0.75,"output":1,"cache_read":0.25,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"google/gemma-4-31B-it","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.4,"agentic_index":4.2,"design_arena_best":null}},{"id":"qwen/qwen3.6-plus","name":"Qwen: Qwen3.6 Plus","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":983616,"uptime_1d":100,"pricing":{"input":0.325,"output":1.95,"cache_read":0.05,"cache_write":0.40625},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.6-plus","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-04","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":54.5,"agentic_index":null,"design_arena_best":{"category":"website","elo":1242,"win_rate":50,"rank":48},"arena_text":1443.05823916263,"arena_text_rank":90,"arena_text_rating_lower":1438.9244329261805,"arena_text_rating_upper":1447.1920453990792,"arena_text_vote_count":48165,"arena_text_date":"2026-10-15","arena_creative_writing":1406.711907632708,"arena_creative_writing_rank":98,"arena_creative_writing_rating_lower":1398.8304945927862,"arena_creative_writing_rating_upper":1414.59332067263,"arena_creative_writing_vote_count":7222,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5v-turbo","name":"Z.ai: GLM 5V Turbo","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","response_format","top_k"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5v-turbo","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-04-01","knowledge_cutoff":null,"description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"androidnative","elo":1267,"win_rate":54.8,"rank":3},"arena_text":1433.736549912949,"arena_text_rank":109,"arena_text_rating_lower":1427.304659531306,"arena_text_rating_upper":1440.168440294592,"arena_text_vote_count":10482,"arena_text_date":"2026-10-15","arena_creative_writing":1407.4475523343403,"arena_creative_writing_rank":96,"arena_creative_writing_rating_lower":1393.176638445531,"arena_creative_writing_rating_upper":1421.7184662231496,"arena_creative_writing_vote_count":1969,"arena_creative_writing_date":"2026-10-15"}},{"id":"x-ai/grok-4.20-multi-agent","name":"SpaceXAI: Grok 4.20 Multi-Agent","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":2000000,"max_completion_tokens":1800000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.25,"output":2.5,"cache_read":0.19999999999999998,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"modelsdev":{"base_url":null,"model_id":"grok-4.20-multi-agent-0309","doc_url":"https://docs.x.ai/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-09","knowledge_cutoff":null,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"x-ai/grok-4.20-multi-agent:priority","name":"SpaceXAI: Grok 4.20 Multi-Agent (priority)","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":2000000,"max_completion_tokens":1800000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":2.5,"output":5,"cache_read":0.39999999999999997,"cache_write":null},"org":"xai","subscription":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"x-ai/grok-4.20","name":"SpaceXAI: Grok 4.20","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":2000000,"max_completion_tokens":1800000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.91666666666667,"pricing":{"input":1.25,"output":2.5,"cache_read":0.19999999999999998,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1228,"win_rate":51.8,"rank":55}}},{"id":"x-ai/grok-4.20:priority","name":"SpaceXAI: Grok 4.20 (priority)","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":2000000,"max_completion_tokens":1800000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","logprobs","top_logprobs","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.5,"output":5,"cache_read":0.39999999999999997,"cache_write":null},"org":"xai","subscription":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1228,"win_rate":51.8,"rank":55}}},{"id":"rekaai/reka-edge","name":"Reka Edge","provider":"reka","provider_display":"Reka","quantization":"unknown","discount":0,"context_length":16384,"max_completion_tokens":14745,"uptime_30m":100,"supported_parameters":["tool_choice","tools","top_k","top_p","stop","seed","temperature","frequency_penalty","presence_penalty","max_tokens","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.09999999999999999,"cache_read":null,"cache_write":null},"org":"rekaai","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.3,"context_length":196608,"max_completion_tokens":176947,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.40425531914893,"pricing":{"input":0.21,"output":0.84,"cache_read":0.041999999999999996,"cache_write":null},"org":"minimax","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"MiniMaxAI/MiniMax-M2.7","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"high","source":"models.dev","release_date":"2026-03-18","knowledge_cutoff":null,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":52.6,"agentic_index":15.3,"design_arena_best":{"category":"website","elo":1241,"win_rate":51.3,"rank":49},"arena_text":1415.0035341569967,"arena_text_rank":140,"arena_text_rating_lower":1411.653118390283,"arena_text_rating_upper":1418.3539499237102,"arena_text_vote_count":84977,"arena_text_date":"2026-10-15","arena_creative_writing":1363.9436635426205,"arena_creative_writing_rank":165,"arena_creative_writing_rating_lower":1357.8156580924347,"arena_creative_writing_rating_upper":1370.071668992806,"arena_creative_writing_vote_count":14495,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.1,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.6551724137931,"pricing":{"input":0.27,"output":1.08,"cache_read":0.054,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"minimax/minimax-m2.7","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-03-18","knowledge_cutoff":null,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":52.6,"agentic_index":15.3,"design_arena_best":{"category":"website","elo":1241,"win_rate":51.3,"rank":49},"arena_text":1415.0035341569967,"arena_text_rank":140,"arena_text_rating_lower":1411.653118390283,"arena_text_rating_upper":1418.3539499237102,"arena_text_vote_count":84977,"arena_text_date":"2026-10-15","arena_creative_writing":1363.9436635426205,"arena_creative_writing_rank":165,"arena_creative_writing_rating_lower":1357.8156580924347,"arena_creative_writing_rating_upper":1370.071668992806,"arena_creative_writing_vote_count":14495,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":196608,"max_completion_tokens":176947,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.45474613686534,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-18","knowledge_cutoff":null,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":52.6,"agentic_index":15.3,"design_arena_best":{"category":"website","elo":1241,"win_rate":51.3,"rank":49},"arena_text":1415.0035341569967,"arena_text_rank":140,"arena_text_rating_lower":1411.653118390283,"arena_text_rating_upper":1418.3539499237102,"arena_text_vote_count":84977,"arena_text_date":"2026-10-15","arena_creative_writing":1363.9436635426205,"arena_creative_writing_rank":165,"arena_creative_writing_rating_lower":1357.8156580924347,"arena_creative_writing_rating_upper":1370.071668992806,"arena_creative_writing_vote_count":14495,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tool_choice","tools"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.36034115138592,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-18","knowledge_cutoff":null,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":52.6,"agentic_index":15.3,"design_arena_best":{"category":"website","elo":1241,"win_rate":51.3,"rank":49},"arena_text":1415.0035341569967,"arena_text_rank":140,"arena_text_rating_lower":1411.653118390283,"arena_text_rating_upper":1418.3539499237102,"arena_text_vote_count":84977,"arena_text_date":"2026-10-15","arena_creative_writing":1363.9436635426205,"arena_creative_writing_rank":165,"arena_creative_writing_rating_lower":1357.8156580924347,"arena_creative_writing_rating_upper":1370.071668992806,"arena_creative_writing_vote_count":14495,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":196608,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":97.55043227665706,"pricing":{"input":0.6,"output":1.7999999999999998,"cache_read":null,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-18","knowledge_cutoff":null,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":52.6,"agentic_index":15.3,"design_arena_best":{"category":"website","elo":1241,"win_rate":51.3,"rank":49},"arena_text":1415.0035341569967,"arena_text_rank":140,"arena_text_rating_lower":1411.653118390283,"arena_text_rating_upper":1418.3539499237102,"arena_text_vote_count":84977,"arena_text_date":"2026-10-15","arena_creative_writing":1363.9436635426205,"arena_creative_writing_rank":165,"arena_creative_writing_rating_lower":1357.8156580924347,"arena_creative_writing_rating_upper":1370.071668992806,"arena_creative_writing_vote_count":14495,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.7:highspeed","name":"MiniMax: MiniMax M2.7 (highspeed)","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tool_choice","tools"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.1981981981982,"pricing":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":null},"org":"minimax","subscription":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":52.6,"agentic_index":15.3,"design_arena_best":{"category":"website","elo":1241,"win_rate":51.3,"rank":49},"arena_text":1415.0035341569967,"arena_text_rank":140,"arena_text_rating_lower":1411.653118390283,"arena_text_rating_upper":1418.3539499237102,"arena_text_vote_count":84977,"arena_text_date":"2026-10-15","arena_creative_writing":1363.9436635426205,"arena_creative_writing_rank":165,"arena_creative_writing_rating_lower":1357.8156580924347,"arena_creative_writing_rating_upper":1370.071668992806,"arena_creative_writing_vote_count":14495,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4-nano:flex","name":"OpenAI: GPT-5.4 Nano (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":96.72131147540983,"pricing":{"input":0.09999999999999999,"output":0.625,"cache_read":0.01,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.1,"agentic_index":16,"design_arena_best":null,"arena_text":1401.189486781593,"arena_text_rank":161,"arena_text_rating_lower":1397.408633326442,"arena_text_rating_upper":1404.9703402367438,"arena_text_vote_count":62396,"arena_text_date":"2026-10-15","arena_creative_writing":1336.7408911543803,"arena_creative_writing_rank":195,"arena_creative_writing_rating_lower":1329.4900650403945,"arena_creative_writing_rating_upper":1343.991717268366,"arena_creative_writing_vote_count":10371,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1.25,"cache_read":0.02,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.4-nano","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.1,"agentic_index":16,"design_arena_best":null,"arena_text":1401.189486781593,"arena_text_rank":161,"arena_text_rating_lower":1397.408633326442,"arena_text_rating_upper":1404.9703402367438,"arena_text_vote_count":62396,"arena_text_date":"2026-10-15","arena_creative_writing":1336.7408911543803,"arena_creative_writing_rank":195,"arena_creative_writing_rating_lower":1329.4900650403945,"arena_creative_writing_rating_upper":1343.991717268366,"arena_creative_writing_vote_count":10371,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1.25,"cache_read":0.02,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.1,"agentic_index":16,"design_arena_best":null,"arena_text":1401.189486781593,"arena_text_rank":161,"arena_text_rating_lower":1397.408633326442,"arena_text_rating_upper":1404.9703402367438,"arena_text_vote_count":62396,"arena_text_date":"2026-10-15","arena_creative_writing":1336.7408911543803,"arena_creative_writing_rank":195,"arena_creative_writing_rating_lower":1329.4900650403945,"arena_creative_writing_rating_upper":1343.991717268366,"arena_creative_writing_vote_count":10371,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4-nano:batch","name":"OpenAI: GPT-5.4 Nano (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":0.09999999999999999,"output":0.625,"cache_read":0.01,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.1,"agentic_index":16,"design_arena_best":null,"arena_text":1401.189486781593,"arena_text_rank":161,"arena_text_rating_lower":1397.408633326442,"arena_text_rating_upper":1404.9703402367438,"arena_text_vote_count":62396,"arena_text_date":"2026-10-15","arena_creative_writing":1336.7408911543803,"arena_creative_writing_rank":195,"arena_creative_writing_rating_lower":1329.4900650403945,"arena_creative_writing_rating_upper":1343.991717268366,"arena_creative_writing_vote_count":10371,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4-mini:flex","name":"OpenAI: GPT-5.4 Mini (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.375,"output":2.25,"cache_read":0.0375,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.1,"coding_index":56.1,"agentic_index":17.9,"design_arena_best":null,"arena_text":1446.9993918152215,"arena_text_rank":85,"arena_text_rating_lower":1443.2518078724324,"arena_text_rating_upper":1450.7469757580106,"arena_text_vote_count":63449,"arena_text_date":"2026-10-15","arena_creative_writing":1401.9458683193252,"arena_creative_writing_rank":107,"arena_creative_writing_rating_lower":1394.8943567669194,"arena_creative_writing_rating_upper":1408.997379871731,"arena_creative_writing_vote_count":10818,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.4-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.1,"coding_index":56.1,"agentic_index":17.9,"design_arena_best":null,"arena_text":1446.9993918152215,"arena_text_rank":85,"arena_text_rating_lower":1443.2518078724324,"arena_text_rating_upper":1450.7469757580106,"arena_text_vote_count":63449,"arena_text_date":"2026-10-15","arena_creative_writing":1401.9458683193252,"arena_creative_writing_rank":107,"arena_creative_writing_rating_lower":1394.8943567669194,"arena_creative_writing_rating_upper":1408.997379871731,"arena_creative_writing_vote_count":10818,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.1,"coding_index":56.1,"agentic_index":17.9,"design_arena_best":null,"arena_text":1446.9993918152215,"arena_text_rank":85,"arena_text_rating_lower":1443.2518078724324,"arena_text_rating_upper":1450.7469757580106,"arena_text_vote_count":63449,"arena_text_date":"2026-10-15","arena_creative_writing":1401.9458683193252,"arena_creative_writing_rank":107,"arena_creative_writing_rating_lower":1394.8943567669194,"arena_creative_writing_rating_upper":1408.997379871731,"arena_creative_writing_vote_count":10818,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4-mini:fast","name":"OpenAI: GPT-5.4 Mini (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.1,"coding_index":56.1,"agentic_index":17.9,"design_arena_best":null,"arena_text":1446.9993918152215,"arena_text_rank":85,"arena_text_rating_lower":1443.2518078724324,"arena_text_rating_upper":1450.7469757580106,"arena_text_vote_count":63449,"arena_text_date":"2026-10-15","arena_creative_writing":1401.9458683193252,"arena_creative_writing_rank":107,"arena_creative_writing_rating_lower":1394.8943567669194,"arena_creative_writing_rating_upper":1408.997379871731,"arena_creative_writing_vote_count":10818,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4-mini:batch","name":"OpenAI: GPT-5.4 Mini (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":0.375,"output":2.25,"cache_read":0.0375,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.1,"coding_index":56.1,"agentic_index":17.9,"design_arena_best":null,"arena_text":1446.9993918152215,"arena_text_rank":85,"arena_text_rating_lower":1443.2518078724324,"arena_text_rating_upper":1450.7469757580106,"arena_text_vote_count":63449,"arena_text_date":"2026-10-15","arena_creative_writing":1401.9458683193252,"arena_creative_writing_rank":107,"arena_creative_writing_rating_lower":1394.8943567669194,"arena_creative_writing_rating_upper":1408.997379871731,"arena_creative_writing_vote_count":10818,"arena_creative_writing_date":"2026-10-15"}},{"id":"mistralai/mistral-small-2603","name":"Mistral: Mistral Small 4","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":209715,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.85152190051967,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"mistral","zdr":true,"modelsdev":{"base_url":null,"model_id":"mistral-small-2603","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"high","source":"models.dev","release_date":"2026-03-16","knowledge_cutoff":"2025-06","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":26.6,"agentic_index":0.8,"design_arena_best":null}},{"id":"z-ai/glm-5-turbo","name":"Z.ai: GLM 5 Turbo","provider":"z-ai","provider_display":"Z.AI","quantization":"unknown","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","response_format","top_k"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5-turbo","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-03-16","knowledge_cutoff":null,"description":"Faster GLM-5 lane for coding agents that need lower latency","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","provider":"dekallm","provider_display":"DekaLLM","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logit_bias","max_tokens","presence_penalty","seed","stop","temperature","top_p","response_format","tools","logprobs","top_logprobs","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.37369519832986,"pricing":{"input":0.08,"output":0.44999999999999996,"cache_read":null,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-11","knowledge_cutoff":"2025-06","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.tokenfactory.nebius.com/","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":37.7,"agentic_index":1.7,"design_arena_best":null}},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.08499999999999999,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-11","knowledge_cutoff":"2025-06","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.tokenfactory.nebius.com/","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":37.7,"agentic_index":1.7,"design_arena_best":null}},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","provider":"crusoe","provider_display":"Crusoe","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":2.4,"cache_read":0.15,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev":{"base_url":"https://api.inference.crusoecloud.com/v1","model_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","doc_url":"https://docs.crusoecloud.com/managed-inference/overview","confidence":"medium","source":"models.dev","release_date":"2026-03-11","knowledge_cutoff":"2025-06","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":37.7,"agentic_index":1.7,"design_arena_best":null}},{"id":"bytedance-seed/seed-2.0-lite","name":"ByteDance Seed: Seed-2.0-Lite","provider":"seed","provider_display":"Seed","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","structured_outputs","tool_choice","tools","response_format","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.25,"output":2,"cache_read":null,"cache_write":null},"org":"bytedance","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","provider":"darkbloom","provider_display":"Darkbloom","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.08,"output":0.13,"cache_read":0.04,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.2,"coding_index":28.7,"agentic_index":1.2,"design_arena_best":null}},{"id":"qwen/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":95.16423357664233,"pricing":{"input":0.09999999999999999,"output":0.15,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3.5-9B","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.2,"coding_index":28.7,"agentic_index":1.2,"design_arena_best":null}},{"id":"qwen/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.25,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.2,"coding_index":28.7,"agentic_index":1.2,"design_arena_best":null}},{"id":"qwen/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","provider":"primeintellect","provider_display":"PrimeIntellect","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":40960,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","tools","tool_choice","temperature","top_p","top_k","min_p","presence_penalty","repetition_penalty","max_tokens","max_completion_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.16999999999999998,"output":0.25,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.2,"coding_index":28.7,"agentic_index":1.2,"design_arena_best":null}},{"id":"qwen/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":96.94444444444444,"pricing":{"input":0.16999999999999998,"output":0.25,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.5-9B","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.2,"coding_index":28.7,"agentic_index":1.2,"design_arena_best":null}},{"id":"openai/gpt-5.4-pro:flex","name":"OpenAI: GPT-5.4 Pro (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":15,"output":90,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":30,"output":180,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":60,"output":270,"cache_read":null,"cache_write":null},{"above_tokens":272000,"input":60,"output":270,"cache_read":null,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"gpt-5.4-pro","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null},{"id":"openai/gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":30,"output":180,"cache_read":null,"cache_write":null},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":60,"output":270,"cache_read":null,"cache_write":null},{"above_tokens":272000,"input":60,"output":270,"cache_read":null,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"gpt-5.4-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null},{"id":"openai/gpt-5.4-pro:batch","name":"OpenAI: GPT-5.4 Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":15,"output":90,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.4:flex","name":"OpenAI: GPT-5.4 (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":0,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":48.31460674157304,"pricing":{"input":1.25,"output":7.5,"cache_read":0.125,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39,"coding_index":71.1,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1237,"win_rate":57.6,"rank":41},"arena_text":1464.7413131497262,"arena_text_rank":55,"arena_text_rating_lower":1461.0529932764323,"arena_text_rating_upper":1468.4296330230204,"arena_text_vote_count":67870,"arena_text_date":"2026-10-15","arena_creative_writing":1434.207884166262,"arena_creative_writing_rank":66,"arena_creative_writing_rating_lower":1427.4115283369497,"arena_creative_writing_rating_upper":1441.0042399955742,"arena_creative_writing_vote_count":11338,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4","name":"OpenAI: GPT-5.4","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":null},"org":"openai","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":5,"output":22.5,"cache_read":0.5,"cache_write":null},{"above_tokens":272000,"input":5,"output":22.5,"cache_read":0.5,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"gpt-5.4","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39,"coding_index":71.1,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1237,"win_rate":57.6,"rank":41},"arena_text":1464.7413131497262,"arena_text_rank":55,"arena_text_rating_lower":1461.0529932764323,"arena_text_rating_upper":1468.4296330230204,"arena_text_vote_count":67870,"arena_text_date":"2026-10-15","arena_creative_writing":1434.207884166262,"arena_creative_writing_rank":66,"arena_creative_writing_rating_lower":1427.4115283369497,"arena_creative_writing_rating_upper":1441.0042399955742,"arena_creative_writing_vote_count":11338,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4","name":"OpenAI: GPT-5.4","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":null},"org":"openai","context_price_tiers":[{"above_tokens":200000,"input":5,"output":22.5,"cache_read":0.5,"cache_write":null},{"above_tokens":272000,"input":5,"output":22.5,"cache_read":0.5,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"gpt-5.4","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39,"coding_index":71.1,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1237,"win_rate":57.6,"rank":41},"arena_text":1464.7413131497262,"arena_text_rank":55,"arena_text_rating_lower":1461.0529932764323,"arena_text_rating_upper":1468.4296330230204,"arena_text_vote_count":67870,"arena_text_date":"2026-10-15","arena_creative_writing":1434.207884166262,"arena_creative_writing_rank":66,"arena_creative_writing_rating_lower":1427.4115283369497,"arena_creative_writing_rating_upper":1441.0042399955742,"arena_creative_writing_vote_count":11338,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4","name":"OpenAI: GPT-5.4","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","tools","tool_choice","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":2.75,"output":16.5,"cache_read":0.275,"cache_write":null},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39,"coding_index":71.1,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1237,"win_rate":57.6,"rank":41},"arena_text":1464.7413131497262,"arena_text_rank":55,"arena_text_rating_lower":1461.0529932764323,"arena_text_rating_upper":1468.4296330230204,"arena_text_vote_count":67870,"arena_text_date":"2026-10-15","arena_creative_writing":1434.207884166262,"arena_creative_writing_rank":66,"arena_creative_writing_rating_lower":1427.4115283369497,"arena_creative_writing_rating_upper":1441.0042399955742,"arena_creative_writing_vote_count":11338,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4:fast","name":"OpenAI: GPT-5.4 (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":100,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39,"coding_index":71.1,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1237,"win_rate":57.6,"rank":41},"arena_text":1464.7413131497262,"arena_text_rank":55,"arena_text_rating_lower":1461.0529932764323,"arena_text_rating_upper":1468.4296330230204,"arena_text_vote_count":67870,"arena_text_date":"2026-10-15","arena_creative_writing":1434.207884166262,"arena_creative_writing_rank":66,"arena_creative_writing_rating_lower":1427.4115283369497,"arena_creative_writing_rating_upper":1441.0042399955742,"arena_creative_writing_vote_count":11338,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.4:batch","name":"OpenAI: GPT-5.4 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":922000,"uptime_1d":null,"pricing":{"input":1.25,"output":7.5,"cache_read":0.125,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":39,"coding_index":71.1,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1237,"win_rate":57.6,"rank":41},"arena_text":1464.7413131497262,"arena_text_rank":55,"arena_text_rating_lower":1461.0529932764323,"arena_text_rating_upper":1468.4296330230204,"arena_text_vote_count":67870,"arena_text_date":"2026-10-15","arena_creative_writing":1434.207884166262,"arena_creative_writing_rank":66,"arena_creative_writing_rating_lower":1427.4115283369497,"arena_creative_writing_rating_upper":1441.0042399955742,"arena_creative_writing_vote_count":11338,"arena_creative_writing_date":"2026-10-15"}},{"id":"inception/mercury-2","name":"Inception: Mercury 2","provider":"inception","provider_display":"Inception","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":50000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","stop","temperature","tools","tool_choice","response_format","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.50445986124876,"pricing":{"input":0.25,"output":0.75,"cache_read":0.024999999999999998,"cache_write":null},"org":"inception","zdr":true,"modelsdev":{"base_url":"https://api.inceptionlabs.ai/v1/","model_id":"mercury-2","doc_url":"https://docs.inceptionlabs.ai/get-started/models","confidence":"high","source":"models.dev","release_date":"2026-02-24","knowledge_cutoff":"2025-01-01","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":10.8,"coding_index":31.1,"agentic_index":1.6,"design_arena_best":{"category":"website","elo":1034,"win_rate":22.1,"rank":127},"arena_text":1343.069006624283,"arena_text_rank":230,"arena_text_rating_lower":1332.5446126662619,"arena_text_rating_upper":1353.5934005823042,"arena_text_vote_count":3197,"arena_text_date":"2026-10-15","arena_creative_writing":1292.9676067744206,"arena_creative_writing_rank":248,"arena_creative_writing_rating_lower":1266.6032120636016,"arena_creative_writing_rating_upper":1319.3320014852393,"arena_creative_writing_vote_count":547,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.1-flash-lite-preview:flex","name":"Google: Gemini 3.1 Flash Lite Preview (flex)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.125,"output":0.75,"cache_read":0.012499999999999999,"cache_write":0.0416666666666667},"org":"google","lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"gemini-3.1-flash-lite-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-03","knowledge_cutoff":"2025-01","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"benchmarks":{"arena_text":1432.9270943558301,"arena_text_rank":110,"arena_text_rating_lower":1429.3054802422857,"arena_text_rating_upper":1436.5487084693743,"arena_text_vote_count":64211,"arena_text_date":"2026-10-15","arena_creative_writing":1414.317968777435,"arena_creative_writing_rank":89,"arena_creative_writing_rating_lower":1407.4610934144926,"arena_creative_writing_rating_upper":1421.1748441403774,"arena_creative_writing_vote_count":10600,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.1-flash-lite-preview:priority","name":"Google: Gemini 3.1 Flash Lite Preview (priority)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","structured_outputs","tool_choice","tools","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.44999999999999996,"output":2.7,"cache_read":0.045,"cache_write":0.15},"org":"google","lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"gemini-3.1-flash-lite-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-03","knowledge_cutoff":"2025-01","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"benchmarks":{"arena_text":1432.9270943558301,"arena_text_rank":110,"arena_text_rating_lower":1429.3054802422857,"arena_text_rating_upper":1436.5487084693743,"arena_text_vote_count":64211,"arena_text_date":"2026-10-15","arena_creative_writing":1414.317968777435,"arena_creative_writing_rank":89,"arena_creative_writing_rating_lower":1407.4610934144926,"arena_creative_writing_rating_upper":1421.1748441403774,"arena_creative_writing_vote_count":10600,"arena_creative_writing_date":"2026-10-15"}},{"id":"bytedance-seed/seed-2.0-mini","name":"ByteDance Seed: Seed-2.0-Mini","provider":"seed","provider_display":"Seed","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"bytedance","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-14","knowledge_cutoff":null,"description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"darkbloom","provider_display":"Darkbloom","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","structured_outputs","logprobs","top_logprobs","tools","response_format","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.89212513484358,"pricing":{"input":0.065,"output":0.75,"cache_read":0.0325,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":19.3,"coding_index":37,"agentic_index":null,"design_arena_best":null,"arena_text":1394.0126320493666,"arena_text_rank":169,"arena_text_rating_lower":1389.7806525536546,"arena_text_rating_upper":1398.2446115450787,"arena_text_vote_count":30457,"arena_text_date":"2026-10-15","arena_creative_writing":1342.8347817996469,"arena_creative_writing_rank":189,"arena_creative_writing_rating_lower":1333.8293445758327,"arena_creative_writing_rating_upper":1351.840219023461,"arena_creative_writing_vote_count":4680,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.9107939339875,"pricing":{"input":0.15,"output":1,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":19.3,"coding_index":37,"agentic_index":null,"design_arena_best":null,"arena_text":1394.0126320493666,"arena_text_rank":169,"arena_text_rating_lower":1389.7806525536546,"arena_text_rating_upper":1398.2446115450787,"arena_text_vote_count":30457,"arena_text_date":"2026-10-15","arena_creative_writing":1342.8347817996469,"arena_creative_writing_rank":189,"arena_creative_writing_rating_lower":1333.8293445758327,"arena_creative_writing_rating_upper":1351.840219023461,"arena_creative_writing_vote_count":4680,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tool_choice","logprobs","response_format","structured_outputs","tools","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.87146529562982,"pricing":{"input":0.15,"output":1,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":19.3,"coding_index":37,"agentic_index":null,"design_arena_best":null,"arena_text":1394.0126320493666,"arena_text_rank":169,"arena_text_rating_lower":1389.7806525536546,"arena_text_rating_upper":1398.2446115450787,"arena_text_vote_count":30457,"arena_text_date":"2026-10-15","arena_creative_writing":1342.8347817996469,"arena_creative_writing_rank":189,"arena_creative_writing_rating_lower":1333.8293445758327,"arena_creative_writing_rating_upper":1351.840219023461,"arena_creative_writing_vote_count":4680,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_logprobs","logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":258048,"uptime_1d":100,"pricing":{"input":0.1625,"output":1.3,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.5-35b-a3b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":19.3,"coding_index":37,"agentic_index":null,"design_arena_best":null,"arena_text":1394.0126320493666,"arena_text_rank":169,"arena_text_rating_lower":1389.7806525536546,"arena_text_rating_upper":1398.2446115450787,"arena_text_vote_count":30457,"arena_text_date":"2026-10-15","arena_creative_writing":1342.8347817996469,"arena_creative_writing_rank":189,"arena_creative_writing_rating_lower":1333.8293445758327,"arena_creative_writing_rating_upper":1351.840219023461,"arena_creative_writing_vote_count":4680,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.22499999999999998,"output":1.7999999999999998,"cache_read":0.22499999999999998,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":19.3,"coding_index":37,"agentic_index":null,"design_arena_best":null,"arena_text":1394.0126320493666,"arena_text_rank":169,"arena_text_rating_lower":1389.7806525536546,"arena_text_rating_upper":1398.2446115450787,"arena_text_vote_count":30457,"arena_text_date":"2026-10-15","arena_creative_writing":1342.8347817996469,"arena_creative_writing_rank":189,"arena_creative_writing_rating_lower":1333.8293445758327,"arena_creative_writing_rating_upper":1351.840219023461,"arena_creative_writing_vote_count":4680,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":76.19047619047619,"pricing":{"input":0.24,"output":1.7999999999999998,"cache_read":0.15,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3.5-35B-A3B","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":19.3,"coding_index":37,"agentic_index":null,"design_arena_best":null,"arena_text":1394.0126320493666,"arena_text_rank":169,"arena_text_rating_lower":1389.7806525536546,"arena_text_rating_upper":1398.2446115450787,"arena_text_vote_count":30457,"arena_text_date":"2026-10-15","arena_creative_writing":1342.8347817996469,"arena_creative_writing_rank":189,"arena_creative_writing_rating_lower":1333.8293445758327,"arena_creative_writing_rating_upper":1351.840219023461,"arena_creative_writing_vote_count":4680,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":93.10344827586206,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_logprobs","logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":258048,"uptime_1d":89.75265017667844,"pricing":{"input":0.195,"output":1.56,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.5-27b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.9,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1408.6798859866929,"arena_text_rank":153,"arena_text_rating_lower":1404.387434481456,"arena_text_rating_upper":1412.9723374919295,"arena_text_vote_count":28671,"arena_text_date":"2026-10-15","arena_creative_writing":1357.6097049465236,"arena_creative_writing_rank":171,"arena_creative_writing_rating_lower":1348.198921054706,"arena_creative_writing_rating_upper":1367.0204888383412,"arena_creative_writing_vote_count":4298,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":91.37055837563452,"pricing":{"input":0.25,"output":2,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3.5-27B","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.9,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1408.6798859866929,"arena_text_rank":153,"arena_text_rating_lower":1404.387434481456,"arena_text_rating_upper":1412.9723374919295,"arena_text_vote_count":28671,"arena_text_date":"2026-10-15","arena_creative_writing":1357.6097049465236,"arena_creative_writing_rank":171,"arena_creative_writing_rating_lower":1348.198921054706,"arena_creative_writing_rating_upper":1367.0204888383412,"arena_creative_writing_vote_count":4298,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.53198127925117,"pricing":{"input":0.27,"output":2.16,"cache_read":0.27,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.9,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1408.6798859866929,"arena_text_rank":153,"arena_text_rating_lower":1404.387434481456,"arena_text_rating_upper":1412.9723374919295,"arena_text_vote_count":28671,"arena_text_date":"2026-10-15","arena_creative_writing":1357.6097049465236,"arena_creative_writing_rank":171,"arena_creative_writing_rating_lower":1348.198921054706,"arena_creative_writing_rating_upper":1367.0204888383412,"arena_creative_writing_vote_count":4298,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.33333333333333,"pricing":{"input":0.3,"output":2.4,"cache_read":0.03,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.9,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1408.6798859866929,"arena_text_rank":153,"arena_text_rating_lower":1404.387434481456,"arena_text_rating_upper":1412.9723374919295,"arena_text_vote_count":28671,"arena_text_date":"2026-10-15","arena_creative_writing":1357.6097049465236,"arena_creative_writing_rank":171,"arena_creative_writing_rating_lower":1348.198921054706,"arena_creative_writing_rating_upper":1367.0204888383412,"arena_creative_writing_vote_count":4298,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":2.4,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3.5-27b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.9,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1408.6798859866929,"arena_text_rank":153,"arena_text_rating_lower":1404.387434481456,"arena_text_rating_upper":1412.9723374919295,"arena_text_vote_count":28671,"arena_text_date":"2026-10-15","arena_creative_writing":1357.6097049465236,"arena_creative_writing_rank":171,"arena_creative_writing_rating_lower":1348.198921054706,"arena_creative_writing_rating_upper":1367.0204888383412,"arena_creative_writing_vote_count":4298,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","repetition_penalty","presence_penalty","max_tokens","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":95.28907922912205,"pricing":{"input":0.26,"output":2.08,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3.5-122B-A10B","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":15.6,"coding_index":45.7,"agentic_index":7.6,"design_arena_best":null,"arena_text":1416.3143007175977,"arena_text_rank":136,"arena_text_rating_lower":1412.0281971034565,"arena_text_rating_upper":1420.6004043317387,"arena_text_vote_count":29732,"arena_text_date":"2026-10-15","arena_creative_writing":1365.2441053019543,"arena_creative_writing_rank":163,"arena_creative_writing_rating_lower":1355.975069517302,"arena_creative_writing_rating_upper":1374.5131410866068,"arena_creative_writing_vote_count":4521,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":258048,"uptime_1d":89.765625,"pricing":{"input":0.26,"output":2.08,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.5-122b-a10b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":15.6,"coding_index":45.7,"agentic_index":7.6,"design_arena_best":null,"arena_text":1416.3143007175977,"arena_text_rank":136,"arena_text_rating_lower":1412.0281971034565,"arena_text_rating_upper":1420.6004043317387,"arena_text_vote_count":29732,"arena_text_date":"2026-10-15","arena_creative_writing":1365.2441053019543,"arena_creative_writing_rank":163,"arena_creative_writing_rating_lower":1355.975069517302,"arena_creative_writing_rating_upper":1374.5131410866068,"arena_creative_writing_vote_count":4521,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.11320754716981,"pricing":{"input":0.3,"output":2.4,"cache_read":0.3,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":15.6,"coding_index":45.7,"agentic_index":7.6,"design_arena_best":null,"arena_text":1416.3143007175977,"arena_text_rank":136,"arena_text_rating_lower":1412.0281971034565,"arena_text_rating_upper":1420.6004043317387,"arena_text_vote_count":29732,"arena_text_date":"2026-10-15","arena_creative_writing":1365.2441053019543,"arena_creative_writing_rank":163,"arena_creative_writing_rating_lower":1355.975069517302,"arena_creative_writing_rating_upper":1374.5131410866068,"arena_creative_writing_vote_count":4521,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":98.07692307692307,"pricing":{"input":0.39999999999999997,"output":3.1999999999999997,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3.5-122b-a10b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":15.6,"coding_index":45.7,"agentic_index":7.6,"design_arena_best":null,"arena_text":1416.3143007175977,"arena_text_rank":136,"arena_text_rating_lower":1412.0281971034565,"arena_text_rating_upper":1420.6004043317387,"arena_text_vote_count":29732,"arena_text_date":"2026-10-15","arena_creative_writing":1365.2441053019543,"arena_creative_writing_rank":163,"arena_creative_writing_rating_lower":1355.975069517302,"arena_creative_writing_rating_upper":1374.5131410866068,"arena_creative_writing_vote_count":4521,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-flash-02-23","name":"Qwen: Qwen3.5-Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":983616,"uptime_1d":100,"pricing":{"input":0.065,"output":0.26,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Google: Gemini 3.1 Pro Preview Custom Tools","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":12,"cache_read":0.19999999999999998,"cache_write":0.375},"org":"google","context_price_tiers":[{"above_tokens":200000,"input":4,"output":18,"cache_read":0.4,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"gemini-3.1-pro-preview-customtools","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-02-19","knowledge_cutoff":"2025-01","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null},{"id":"openai/gpt-5.3-codex","name":"OpenAI: GPT-5.3-Codex","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.3-codex","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-02-24","knowledge_cutoff":"2025-08-31","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":32.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1164,"win_rate":50.6,"rank":76}}},{"id":"openai/gpt-5.3-codex","name":"OpenAI: GPT-5.3-Codex","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.3-codex","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-02-05","knowledge_cutoff":"2025-08-31","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":32.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1164,"win_rate":50.6,"rank":76}}},{"id":"openai/gpt-5.3-codex:fast","name":"OpenAI: GPT-5.3-Codex (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":3.5,"output":28,"cache_read":0.35,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.3-codex","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-02-05","knowledge_cutoff":"2025-08-31","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":32.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1164,"win_rate":50.6,"rank":76}}},{"id":"aion-labs/aion-2.0","name":"AionLabs: Aion-2.0","provider":"aionlabs","provider_display":"AionLabs","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7999999999999999,"output":1.5999999999999999,"cache_read":0.19999999999999998,"cache_write":null},"org":"aion-labs","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"google/gemini-3.1-pro-preview:flex","name":"Google: Gemini 3.1 Pro Preview (flex)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":3.9215686274509802,"pricing":{"input":1,"output":6,"cache_read":0.09999999999999999,"cache_write":0.1875},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.1-pro-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-02-19","knowledge_cutoff":"2025-01","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":8.2,"design_arena_best":{"category":"svg","elo":1283,"win_rate":67.8,"rank":12},"arena_text":1486.9094358879568,"arena_text_rank":19,"arena_text_rating_lower":1483.9491002818586,"arena_text_rating_upper":1489.869771494055,"arena_text_vote_count":127649,"arena_text_date":"2026-10-15","arena_creative_writing":1480.996930948638,"arena_creative_writing_rank":12,"arena_creative_writing_rating_lower":1475.677482894711,"arena_creative_writing_rating_upper":1486.3163790025653,"arena_creative_writing_vote_count":23619,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.86111111111111,"pricing":{"input":2,"output":12,"cache_read":0.19999999999999998,"cache_write":0.375},"org":"google","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":4,"output":18,"cache_read":0.4,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"gemini-3.1-pro-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-02-19","knowledge_cutoff":"2025-01","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.7,"coding_index":68.8,"agentic_index":8.2,"design_arena_best":{"category":"svg","elo":1283,"win_rate":67.8,"rank":12},"arena_text":1486.9094358879568,"arena_text_rank":19,"arena_text_rating_lower":1483.9491002818586,"arena_text_rating_upper":1489.869771494055,"arena_text_vote_count":127649,"arena_text_date":"2026-10-15","arena_creative_writing":1480.996930948638,"arena_creative_writing_rank":12,"arena_creative_writing_rating_lower":1475.677482894711,"arena_creative_writing_rating_upper":1486.3163790025653,"arena_creative_writing_vote_count":23619,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.1-pro-preview:priority","name":"Google: Gemini 3.1 Pro Preview (priority)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3.5999999999999996,"output":21.6,"cache_read":0.36,"cache_write":0.675},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.1-pro-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-02-19","knowledge_cutoff":"2025-01","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":8.2,"design_arena_best":{"category":"svg","elo":1283,"win_rate":67.8,"rank":12},"arena_text":1486.9094358879568,"arena_text_rank":19,"arena_text_rating_lower":1483.9491002818586,"arena_text_rating_upper":1489.869771494055,"arena_text_vote_count":127649,"arena_text_date":"2026-10-15","arena_creative_writing":1480.996930948638,"arena_creative_writing_rank":12,"arena_creative_writing_rating_lower":1475.677482894711,"arena_creative_writing_rating_upper":1486.3163790025653,"arena_creative_writing_vote_count":23619,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3.1-pro-preview:batch","name":"Google: Gemini 3.1 Pro Preview (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1,"output":6,"cache_read":0.2,"cache_write":null},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.1-pro-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-02-19","knowledge_cutoff":"2025-01","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":8.2,"design_arena_best":{"category":"svg","elo":1283,"win_rate":67.8,"rank":12},"arena_text":1486.9094358879568,"arena_text_rank":19,"arena_text_rating_lower":1483.9491002818586,"arena_text_rating_upper":1489.869771494055,"arena_text_vote_count":127649,"arena_text_date":"2026-10-15","arena_creative_writing":1480.996930948638,"arena_creative_writing_rank":12,"arena_creative_writing_rating_lower":1475.677482894711,"arena_creative_writing_rating_upper":1486.3163790025653,"arena_creative_writing_vote_count":23619,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-17","knowledge_cutoff":"2025-08-31","description":"Claude workhorse for coding agents, careful analysis, and production cost control","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.7,"coding_index":63,"agentic_index":31.8,"design_arena_best":{"category":"website","elo":1283,"win_rate":60,"rank":23}}},{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","response_format","verbosity","top_k","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-17","knowledge_cutoff":"2025-08-31","description":"Claude workhorse for coding agents, careful analysis, and production cost control","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.7,"coding_index":63,"agentic_index":31.8,"design_arena_best":{"category":"website","elo":1283,"win_rate":60,"rank":23}}},{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-17","knowledge_cutoff":"2025-08-31","description":"Claude workhorse for coding agents, careful analysis, and production cost control","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.7,"coding_index":63,"agentic_index":31.8,"design_arena_best":{"category":"website","elo":1283,"win_rate":60,"rank":23}}},{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.7,"coding_index":63,"agentic_index":31.8,"design_arena_best":{"category":"website","elo":1283,"win_rate":60,"rank":23}}},{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice","verbosity","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.68602825745683,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-17","knowledge_cutoff":"2025-08-31","description":"Claude workhorse for coding agents, careful analysis, and production cost control","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.7,"coding_index":63,"agentic_index":31.8,"design_arena_best":{"category":"website","elo":1283,"win_rate":60,"rank":23}}},{"id":"anthropic/claude-sonnet-4.6:batch","name":"Anthropic: Claude Sonnet 4.6 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","tools","tool_choice","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1.5,"output":7.5,"cache_read":0.15,"cache_write":1.875},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.7,"coding_index":63,"agentic_index":31.8,"design_arena_best":{"category":"website","elo":1283,"win_rate":60,"rank":23}}},{"id":"qwen/qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":983616,"uptime_1d":99.47201689545935,"pricing":{"input":0.26,"output":1.56,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1187,"win_rate":50,"rank":72}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","presence_penalty","response_format","tool_choice","tools","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":258048,"uptime_1d":99.34924078091106,"pricing":{"input":0.39,"output":2.34,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.5-397b-a17b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.4,"coding_index":48.2,"agentic_index":8.3,"design_arena_best":{"category":"website","elo":1189,"win_rate":52.5,"rank":70},"arena_text":1441.5655970064536,"arena_text_rank":94,"arena_text_rating_lower":1438.475745273247,"arena_text_rating_upper":1444.6554487396604,"arena_text_vote_count":93567,"arena_text_date":"2026-10-15","arena_creative_writing":1405.830251014268,"arena_creative_writing_rank":100,"arena_creative_writing_rating_lower":1400.1870528811276,"arena_creative_writing_rating_upper":1411.4734491474082,"arena_creative_writing_vote_count":16543,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.74640743871514,"pricing":{"input":0.5,"output":3.5999999999999996,"cache_read":0.3,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.4,"coding_index":48.2,"agentic_index":8.3,"design_arena_best":{"category":"website","elo":1189,"win_rate":52.5,"rank":70},"arena_text":1441.5655970064536,"arena_text_rank":94,"arena_text_rating_lower":1438.475745273247,"arena_text_rating_upper":1444.6554487396604,"arena_text_vote_count":93567,"arena_text_date":"2026-10-15","arena_creative_writing":1405.830251014268,"arena_creative_writing_rank":100,"arena_creative_writing_rating_lower":1400.1870528811276,"arena_creative_writing_rating_upper":1411.4734491474082,"arena_creative_writing_vote_count":16543,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","structured_outputs","response_format","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":93.99141630901288,"pricing":{"input":0.55,"output":3.5,"cache_read":0.11,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"qwen3.5-397b-a17b","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.4,"coding_index":48.2,"agentic_index":8.3,"design_arena_best":{"category":"website","elo":1189,"win_rate":52.5,"rank":70},"arena_text":1441.5655970064536,"arena_text_rank":94,"arena_text_rating_lower":1438.475745273247,"arena_text_rating_upper":1444.6554487396604,"arena_text_vote_count":93567,"arena_text_date":"2026-10-15","arena_creative_writing":1405.830251014268,"arena_creative_writing_rank":100,"arena_creative_writing_rating_lower":1400.1870528811276,"arena_creative_writing_rating_upper":1411.4734491474082,"arena_creative_writing_vote_count":16543,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.06687402799378,"pricing":{"input":0.55,"output":3.5,"cache_read":0.22499999999999998,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.4,"coding_index":48.2,"agentic_index":8.3,"design_arena_best":{"category":"website","elo":1189,"win_rate":52.5,"rank":70},"arena_text":1441.5655970064536,"arena_text_rank":94,"arena_text_rating_lower":1438.475745273247,"arena_text_rating_upper":1444.6554487396604,"arena_text_vote_count":93567,"arena_text_date":"2026-10-15","arena_creative_writing":1405.830251014268,"arena_creative_writing_rank":100,"arena_creative_writing_rating_lower":1400.1870528811276,"arena_creative_writing_rating_upper":1411.4734491474082,"arena_creative_writing_vote_count":16543,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":93.2975871313673,"pricing":{"input":0.55,"output":3.5,"cache_read":0.55,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.4,"coding_index":48.2,"agentic_index":8.3,"design_arena_best":{"category":"website","elo":1189,"win_rate":52.5,"rank":70},"arena_text":1441.5655970064536,"arena_text_rank":94,"arena_text_rating_lower":1438.475745273247,"arena_text_rating_upper":1444.6554487396604,"arena_text_vote_count":93567,"arena_text_date":"2026-10-15","arena_creative_writing":1405.830251014268,"arena_creative_writing_rank":100,"arena_creative_writing_rating_lower":1400.1870528811276,"arena_creative_writing_rating_upper":1411.4734491474082,"arena_creative_writing_vote_count":16543,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop","presence_penalty"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":95.4233409610984,"pricing":{"input":0.6,"output":3.5999999999999996,"cache_read":0.12,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.4,"coding_index":48.2,"agentic_index":8.3,"design_arena_best":{"category":"website","elo":1189,"win_rate":52.5,"rank":70},"arena_text":1441.5655970064536,"arena_text_rank":94,"arena_text_rating_lower":1438.475745273247,"arena_text_rating_upper":1444.6554487396604,"arena_text_vote_count":93567,"arena_text_date":"2026-10-15","arena_creative_writing":1405.830251014268,"arena_creative_writing_rank":100,"arena_creative_writing_rating_lower":1400.1870528811276,"arena_creative_writing_rating_upper":1411.4734491474082,"arena_creative_writing_vote_count":16543,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":55.55555555555556,"pricing":{"input":0.6,"output":3.5999999999999996,"cache_read":null,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.4,"coding_index":48.2,"agentic_index":8.3,"design_arena_best":{"category":"website","elo":1189,"win_rate":52.5,"rank":70},"arena_text":1441.5655970064536,"arena_text_rank":94,"arena_text_rating_lower":1438.475745273247,"arena_text_rating_upper":1444.6554487396604,"arena_text_vote_count":93567,"arena_text_date":"2026-10-15","arena_creative_writing":1405.830251014268,"arena_creative_writing_rank":100,"arena_creative_writing_rating_lower":1400.1870528811276,"arena_creative_writing_rating_upper":1411.4734491474082,"arena_creative_writing_vote_count":16543,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.18032786885246,"pricing":{"input":0.6,"output":3.5999999999999996,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3.5-397b-a17b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.4,"coding_index":48.2,"agentic_index":8.3,"design_arena_best":{"category":"website","elo":1189,"win_rate":52.5,"rank":70},"arena_text":1441.5655970064536,"arena_text_rank":94,"arena_text_rating_lower":1438.475745273247,"arena_text_rating_upper":1444.6554487396604,"arena_text_vote_count":93567,"arena_text_date":"2026-10-15","arena_creative_writing":1405.830251014268,"arena_creative_writing_rank":100,"arena_creative_writing_rating_lower":1400.1870528811276,"arena_creative_writing_rating_upper":1411.4734491474082,"arena_creative_writing_vote_count":16543,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":92.57294429708223,"pricing":{"input":0.75,"output":4.5,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.4,"coding_index":48.2,"agentic_index":8.3,"design_arena_best":{"category":"website","elo":1189,"win_rate":52.5,"rank":70},"arena_text":1441.5655970064536,"arena_text_rank":94,"arena_text_rating_lower":1438.475745273247,"arena_text_rating_upper":1444.6554487396604,"arena_text_vote_count":93567,"arena_text_date":"2026-10-15","arena_creative_writing":1405.830251014268,"arena_creative_writing_rank":100,"arena_creative_writing_rating_lower":1400.1870528811276,"arena_creative_writing_rating_upper":1411.4734491474082,"arena_creative_writing_vote_count":16543,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":198000,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.5632183908046,"pricing":{"input":0.27,"output":0.95,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"modified-mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1222,"win_rate":57.5,"rank":59},"arena_text":1390.6393248159263,"arena_text_rank":176,"arena_text_rating_lower":1386.7507469142622,"arena_text_rating_upper":1394.5279027175907,"arena_text_vote_count":42815,"arena_text_date":"2026-10-15","arena_creative_writing":1356.158261008215,"arena_creative_writing_rank":173,"arena_creative_writing_rating_lower":1348.2833131092946,"arena_creative_writing_rating_upper":1364.0332089071358,"arena_creative_writing_vote_count":6671,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0.1,"context_length":200000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.27,"output":1.08,"cache_read":0.027,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"modified-mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1222,"win_rate":57.5,"rank":59},"arena_text":1390.6393248159263,"arena_text_rank":176,"arena_text_rating_lower":1386.7507469142622,"arena_text_rating_upper":1394.5279027175907,"arena_text_vote_count":42815,"arena_text_date":"2026-10-15","arena_creative_writing":1356.158261008215,"arena_creative_writing_rank":173,"arena_creative_writing_rating_lower":1348.2833131092946,"arena_creative_writing_rating_upper":1364.0332089071358,"arena_creative_writing_vote_count":6671,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":196608,"max_completion_tokens":176947,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","structured_outputs","response_format","seed","stop","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.295,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"modified-mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1222,"win_rate":57.5,"rank":59},"arena_text":1390.6393248159263,"arena_text_rank":176,"arena_text_rating_lower":1386.7507469142622,"arena_text_rating_upper":1394.5279027175907,"arena_text_vote_count":42815,"arena_text_date":"2026-10-15","arena_creative_writing":1356.158261008215,"arena_creative_writing_rank":173,"arena_creative_writing_rating_lower":1348.2833131092946,"arena_creative_writing_rating_upper":1364.0332089071358,"arena_creative_writing_vote_count":6671,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0,"context_length":196608,"max_completion_tokens":176947,"uptime_30m":50,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":96.36363636363636,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"modified-mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1222,"win_rate":57.5,"rank":59},"arena_text":1390.6393248159263,"arena_text_rank":176,"arena_text_rating_lower":1386.7507469142622,"arena_text_rating_upper":1394.5279027175907,"arena_text_vote_count":42815,"arena_text_date":"2026-10-15","arena_creative_writing":1356.158261008215,"arena_creative_writing_rank":173,"arena_creative_writing_rating_lower":1348.2833131092946,"arena_creative_writing_rating_upper":1364.0332089071358,"arena_creative_writing_vote_count":6671,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":65536,"max_completion_tokens":58982,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","structured_outputs","response_format","tool_choice","tools","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"minimax-m2.5","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":"2025-08","description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"modified-mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1222,"win_rate":57.5,"rank":59},"arena_text":1390.6393248159263,"arena_text_rank":176,"arena_text_rating_lower":1386.7507469142622,"arena_text_rating_upper":1394.5279027175907,"arena_text_vote_count":42815,"arena_text_date":"2026-10-15","arena_creative_writing":1356.158261008215,"arena_creative_writing_rank":173,"arena_creative_writing_rating_lower":1348.2833131092946,"arena_creative_writing_rating_upper":1364.0332089071358,"arena_creative_writing_vote_count":6671,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131100,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.35622317596567,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"minimax/minimax-m2.5","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"modified-mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1222,"win_rate":57.5,"rank":59},"arena_text":1390.6393248159263,"arena_text_rank":176,"arena_text_rating_lower":1386.7507469142622,"arena_text_rating_upper":1394.5279027175907,"arena_text_vote_count":42815,"arena_text_date":"2026-10-15","arena_creative_writing":1356.158261008215,"arena_creative_writing_rank":173,"arena_creative_writing_rating_lower":1348.2833131092946,"arena_creative_writing_rating_upper":1364.0332089071358,"arena_creative_writing_vote_count":6671,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tool_choice","tools"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"modified-mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1222,"win_rate":57.5,"rank":59},"arena_text":1390.6393248159263,"arena_text_rank":176,"arena_text_rating_lower":1386.7507469142622,"arena_text_rating_upper":1394.5279027175907,"arena_text_vote_count":42815,"arena_text_date":"2026-10-15","arena_creative_writing":1356.158261008215,"arena_creative_writing_rank":173,"arena_creative_writing_rating_lower":1348.2833131092946,"arena_creative_writing_rating_upper":1364.0332089071358,"arena_creative_writing_vote_count":6671,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.5:highspeed","name":"MiniMax: MiniMax M2.5 (highspeed)","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":97.77777777777777,"pricing":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":null},"org":"minimax","subscription":true,"open_weights":true,"open_weights_source":"override","license":"modified-mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1222,"win_rate":57.5,"rank":59},"arena_text":1390.6393248159263,"arena_text_rank":176,"arena_text_rating_lower":1386.7507469142622,"arena_text_rating_upper":1394.5279027175907,"arena_text_vote_count":42815,"arena_text_date":"2026-10-15","arena_creative_writing":1356.158261008215,"arena_creative_writing_rank":173,"arena_creative_writing_rating_lower":1348.2833131092946,"arena_creative_writing_rating_upper":1364.0332089071358,"arena_creative_writing_vote_count":6671,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.4,"context_length":198000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","tool_choice","tools","max_tokens","temperature","top_p","stop","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6,"output":1.92,"cache_read":0.12,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.4,"context_length":202752,"max_completion_tokens":182476,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.72202918693537,"pricing":{"input":0.6,"output":1.92,"cache_read":0.12,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"zai-org/GLM-5-FP8","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"medium","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","tool_choice","tools","response_format","structured_outputs","frequency_penalty","presence_penalty","repetition_penalty","stop","seed"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7,"output":2.24,"cache_read":0.14,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.9107939339875,"pricing":{"input":0.95,"output":2.5500000000000003,"cache_read":0.19999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"zai-org/GLM-5","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","tools","tool_choice","seed"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":3.1999999999999997,"cache_read":null,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"zai.glm-5","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":198000,"max_completion_tokens":32000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":3.1999999999999997,"cache_read":0.19999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":202800,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":3.1999999999999997,"cache_read":0.19999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-5","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":3.1999999999999997,"cache_read":0.19999999999999998,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-5:turbo","name":"Z.ai: GLM 5 (turbo)","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32768,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":null},"org":"z-ai","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1264,"win_rate":55,"rank":29},"arena_text":1457.2666631824843,"arena_text_rank":65,"arena_text_rating_lower":1453.0235883683322,"arena_text_rating_upper":1461.5097379966364,"arena_text_vote_count":29272,"arena_text_date":"2026-10-15","arena_creative_writing":1447.5196815042978,"arena_creative_writing_rank":42,"arena_creative_writing_rating_lower":1438.5515855717422,"arena_creative_writing_rating_upper":1456.487777436853,"arena_creative_writing_vote_count":4852,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-05","knowledge_cutoff":"2025-05-31","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1290,"win_rate":61.1,"rank":20},"arena_text":1497.209105729648,"arena_text_rank":8,"arena_text_rating_lower":1493.9537105713546,"arena_text_rating_upper":1500.4645008879415,"arena_text_vote_count":86071,"arena_text_date":"2026-10-15","arena_creative_writing":1477.88964739441,"arena_creative_writing_rank":13,"arena_creative_writing_rating_lower":1471.831385171791,"arena_creative_writing_rating_upper":1483.9479096170294,"arena_creative_writing_vote_count":15116,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","response_format","verbosity","top_k","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-05","knowledge_cutoff":"2025-05-31","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1290,"win_rate":61.1,"rank":20},"arena_text":1497.209105729648,"arena_text_rank":8,"arena_text_rating_lower":1493.9537105713546,"arena_text_rating_upper":1500.4645008879415,"arena_text_vote_count":86071,"arena_text_date":"2026-10-15","arena_creative_writing":1477.88964739441,"arena_creative_writing_rank":13,"arena_creative_writing_rating_lower":1471.831385171791,"arena_creative_writing_rating_upper":1483.9479096170294,"arena_creative_writing_vote_count":15116,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tool_choice","tools","verbosity","structured_outputs","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-05","knowledge_cutoff":"2025-05-31","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1290,"win_rate":61.1,"rank":20},"arena_text":1497.209105729648,"arena_text_rank":8,"arena_text_rating_lower":1493.9537105713546,"arena_text_rating_upper":1500.4645008879415,"arena_text_vote_count":86071,"arena_text_date":"2026-10-15","arena_creative_writing":1477.88964739441,"arena_creative_writing_rank":13,"arena_creative_writing_rating_lower":1471.831385171791,"arena_creative_writing_rating_upper":1483.9479096170294,"arena_creative_writing_vote_count":15116,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tool_choice","tools","response_format","verbosity","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1290,"win_rate":61.1,"rank":20},"arena_text":1497.209105729648,"arena_text_rank":8,"arena_text_rating_lower":1493.9537105713546,"arena_text_rating_upper":1500.4645008879415,"arena_text_vote_count":86071,"arena_text_date":"2026-10-15","arena_creative_writing":1477.88964739441,"arena_creative_writing_rank":13,"arena_creative_writing_rating_lower":1471.831385171791,"arena_creative_writing_rating_upper":1483.9479096170294,"arena_creative_writing_vote_count":15116,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-05","knowledge_cutoff":"2025-05-31","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1290,"win_rate":61.1,"rank":20},"arena_text":1497.209105729648,"arena_text_rank":8,"arena_text_rating_lower":1493.9537105713546,"arena_text_rating_upper":1500.4645008879415,"arena_text_vote_count":86071,"arena_text_date":"2026-10-15","arena_creative_writing":1477.88964739441,"arena_creative_writing_rank":13,"arena_creative_writing_rating_lower":1471.831385171791,"arena_creative_writing_rating_upper":1483.9479096170294,"arena_creative_writing_vote_count":15116,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.6:batch","name":"Anthropic: Claude Opus 4.6 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","tool_choice","tools","structured_outputs","response_format","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1290,"win_rate":61.1,"rank":20},"arena_text":1497.209105729648,"arena_text_rank":8,"arena_text_rating_lower":1493.9537105713546,"arena_text_rating_upper":1500.4645008879415,"arena_text_vote_count":86071,"arena_text_date":"2026-10-15","arena_creative_writing":1477.88964739441,"arena_creative_writing_rank":13,"arena_creative_writing_rating_lower":1471.831385171791,"arena_creative_writing_rating_upper":1483.9479096170294,"arena_creative_writing_vote_count":15116,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.12,"output":0.7999999999999999,"cache_read":0.07,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-03","knowledge_cutoff":"2025-09","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":36.2,"agentic_index":0.9,"design_arena_best":null}},{"id":"stepfun/step-3.5-flash","name":"StepFun: Step 3.5 Flash","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.04761904761905,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":null,"cache_write":null},"org":"stepfun","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"stepfun-ai/Step-3.5-Flash","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-01-29","knowledge_cutoff":"2025-01","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":17,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1392.8156971671676,"arena_text_rank":171,"arena_text_rating_lower":1389.2627102562321,"arena_text_rating_upper":1396.368684078103,"arena_text_vote_count":60332,"arena_text_date":"2026-10-15","arena_creative_writing":1344.8205205184015,"arena_creative_writing_rank":183,"arena_creative_writing_rating_lower":1338.0502854958693,"arena_creative_writing_rating_upper":1351.5907555409337,"arena_creative_writing_vote_count":9775,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","seed","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":95.57321225879683,"pricing":{"input":0.49,"output":2.5,"cache_read":0.19999999999999998,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-27","knowledge_cutoff":"2025-01","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.5,"coding_index":46.8,"agentic_index":null,"design_arena_best":{"category":"website","elo":1248,"win_rate":55.2,"rank":45}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","response_format","tools","tool_choice","structured_outputs","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.5,"output":2.5,"cache_read":0.15,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"moonshotai/Kimi-K2.5","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2026-01-27","knowledge_cutoff":"2025-01","description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.5,"coding_index":46.8,"agentic_index":null,"design_arena_best":{"category":"website","elo":1248,"win_rate":55.2,"rank":45}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0.05,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.532,"output":3.3249999999999997,"cache_read":0.20900000000000002,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-27","knowledge_cutoff":"2025-01","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.5,"coding_index":46.8,"agentic_index":null,"design_arena_best":{"category":"website","elo":1248,"win_rate":55.2,"rank":45}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0.05,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":96.8,"pricing":{"input":0.5700000000000001,"output":2.8499999999999996,"cache_read":0.095,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"moonshotai/kimi-k2.5","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-01-27","knowledge_cutoff":"2025-01","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.5,"coding_index":46.8,"agentic_index":null,"design_arena_best":{"category":"website","elo":1248,"win_rate":55.2,"rank":45}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","seed","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6,"output":3,"cache_read":null,"cache_write":null},"org":"moonshot","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.5,"coding_index":46.8,"agentic_index":null,"design_arena_best":{"category":"website","elo":1248,"win_rate":55.2,"rank":45}}},{"id":"minimax/minimax-m2-her","name":"MiniMax: MiniMax M2-her","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":65536,"max_completion_tokens":2048,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":80.21877848678214,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","subscription":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"writer/palmyra-x5","name":"Writer: Palmyra X5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1040000,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":1040000,"uptime_1d":100,"pricing":{"input":0.6,"output":6,"cache_read":null,"cache_write":null},"org":"writer","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"writer.palmyra-x5-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2025-04-28","knowledge_cutoff":null,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null},{"id":"z-ai/glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","min_p","stop","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.060500000000000005,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/zai-org/glm-4.7-flash","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-01-19","knowledge_cutoff":"2025-04","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":14.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1202,"win_rate":57.6,"rank":60},"arena_text":1364.5160203965402,"arena_text_rank":201,"arena_text_rating_lower":1358.8016752228536,"arena_text_rating_upper":1370.230365570227,"arena_text_vote_count":12021,"arena_text_date":"2026-10-15","arena_creative_writing":1304.7675155862905,"arena_creative_writing_rank":230,"arena_creative_writing_rating_lower":1291.0131953224686,"arena_creative_writing_rating_upper":1318.5218358501124,"arena_creative_writing_vote_count":1873,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":200000,"max_completion_tokens":128000,"uptime_30m":3.3333333333333335,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":1.1111111111111112,"pricing":{"input":0.07,"output":0.39999999999999997,"cache_read":0.01,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.7-flash","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-01-19","knowledge_cutoff":"2025-04","description":"Budget GLM lane for fast coding help, routing, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":14.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1202,"win_rate":57.6,"rank":60},"arena_text":1364.5160203965402,"arena_text_rank":201,"arena_text_rating_lower":1358.8016752228536,"arena_text_rating_upper":1370.230365570227,"arena_text_vote_count":12021,"arena_text_date":"2026-10-15","arena_creative_writing":1304.7675155862905,"arena_creative_writing_rank":230,"arena_creative_writing_rating_lower":1291.0131953224686,"arena_creative_writing_rating_upper":1318.5218358501124,"arena_creative_writing_vote_count":1873,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.2-codex","name":"OpenAI: GPT-5.2-Codex","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.2-codex","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-01-14","knowledge_cutoff":"2025-08-31","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.5,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"androidnative","elo":1176,"win_rate":47.5,"rank":18}}},{"id":"bytedance-seed/seed-1.6-flash","name":"ByteDance Seed: Seed 1.6 Flash","provider":"seed","provider_display":"Seed","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.075,"output":0.3,"cache_read":null,"cache_write":null},"org":"bytedance","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"bytedance-seed/seed-1.6","name":"ByteDance Seed: Seed 1.6","provider":"seed","provider_display":"Seed","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","temperature","top_p","tools","tool_choice","response_format","structured_outputs","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.25,"output":2,"cache_read":null,"cache_write":null},"org":"bytedance","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"minimax/minimax-m2.1","name":"MiniMax: MiniMax M2.1","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":84.61538461538461,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":86.20689655172413,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-23","knowledge_cutoff":null,"description":"Earlier MiniMax agent model for practical coding and productivity tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1218,"win_rate":60.9,"rank":53},"arena_text":1384.437854918656,"arena_text_rank":185,"arena_text_rating_lower":1379.2613612323398,"arena_text_rating_upper":1389.6143486049723,"arena_text_vote_count":17239,"arena_text_date":"2026-10-15","arena_creative_writing":1344.6339928484797,"arena_creative_writing_rank":185,"arena_creative_writing_rating_lower":1333.1870444720157,"arena_creative_writing_rating_upper":1356.0809412249437,"arena_creative_writing_vote_count":2808,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m2.1:highspeed","name":"MiniMax: MiniMax M2.1 (highspeed)","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":85.71428571428571,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tool_choice","tools"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":70.83333333333334,"pricing":{"input":0.3,"output":2.4,"cache_read":0.03,"cache_write":null},"org":"minimax","subscription":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1218,"win_rate":60.9,"rank":53},"arena_text":1384.437854918656,"arena_text_rank":185,"arena_text_rating_lower":1379.2613612323398,"arena_text_rating_upper":1389.6143486049723,"arena_text_vote_count":17239,"arena_text_date":"2026-10-15","arena_creative_writing":1344.6339928484797,"arena_creative_writing_rank":185,"arena_creative_writing_rating_lower":1333.1870444720157,"arena_creative_writing_rating_upper":1356.0809412249437,"arena_creative_writing_vote_count":2808,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.7:flex","name":"Z.ai: GLM 4.7 (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.32,"output":1.4,"cache_read":0.064,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":null,"model_id":"zai-org/GLM-4.7","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.2,"coding_index":45.3,"agentic_index":null,"design_arena_best":{"category":"website","elo":1224,"win_rate":55.3,"rank":57},"arena_text":1441.3266291777354,"arena_text_rank":95,"arena_text_rating_lower":1435.2694154856003,"arena_text_rating_upper":1447.3838428698703,"arena_text_vote_count":12253,"arena_text_date":"2026-10-15","arena_creative_writing":1404.7365646711344,"arena_creative_writing_rank":102,"arena_creative_writing_rating_lower":1391.4905429408939,"arena_creative_writing_rating_upper":1417.9825864013746,"arena_creative_writing_vote_count":1960,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"venice","provider_display":"Venice","quantization":"fp4","discount":0.272,"context_length":198000,"max_completion_tokens":16384,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.40040000000000003,"output":1.9292,"cache_read":0.08008,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.2,"coding_index":45.3,"agentic_index":null,"design_arena_best":{"category":"website","elo":1224,"win_rate":55.3,"rank":57},"arena_text":1441.3266291777354,"arena_text_rank":95,"arena_text_rating_lower":1435.2694154856003,"arena_text_rating_upper":1447.3838428698703,"arena_text_vote_count":12253,"arena_text_date":"2026-10-15","arena_creative_writing":1404.7365646711344,"arena_creative_writing_rank":102,"arena_creative_writing_rating_lower":1391.4905429408939,"arena_creative_writing_rating_upper":1417.9825864013746,"arena_creative_writing_vote_count":1960,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.1,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.65277777777779,"pricing":{"input":0.54,"output":1.9800000000000002,"cache_read":0.099,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.7","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.2,"coding_index":45.3,"agentic_index":null,"design_arena_best":{"category":"website","elo":1224,"win_rate":55.3,"rank":57},"arena_text":1441.3266291777354,"arena_text_rank":95,"arena_text_rating_lower":1435.2694154856003,"arena_text_rating_upper":1447.3838428698703,"arena_text_vote_count":12253,"arena_text_date":"2026-10-15","arena_creative_writing":1404.7365646711344,"arena_creative_writing_rank":102,"arena_creative_writing_rating_lower":1391.4905429408939,"arena_creative_writing_rating_upper":1417.9825864013746,"arena_creative_writing_vote_count":1960,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"z-ai","provider_display":"Z.AI","quantization":"fp4","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.7","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.2,"coding_index":45.3,"agentic_index":null,"design_arena_best":{"category":"website","elo":1224,"win_rate":55.3,"rank":57},"arena_text":1441.3266291777354,"arena_text_rank":95,"arena_text_rating_lower":1435.2694154856003,"arena_text_rating_upper":1447.3838428698703,"arena_text_vote_count":12253,"arena_text_date":"2026-10-15","arena_creative_writing":1404.7365646711344,"arena_creative_writing_rank":102,"arena_creative_writing_rating_lower":1391.4905429408939,"arena_creative_writing_rating_upper":1417.9825864013746,"arena_creative_writing_vote_count":1960,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a"],"supports_tool_choice":false,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7,"output":2.5,"cache_read":null,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22.2,"coding_index":45.3,"agentic_index":null,"design_arena_best":{"category":"website","elo":1224,"win_rate":55.3,"rank":57},"arena_text":1441.3266291777354,"arena_text_rank":95,"arena_text_rating_lower":1435.2694154856003,"arena_text_rating_upper":1447.3838428698703,"arena_text_vote_count":12253,"arena_text_date":"2026-10-15","arena_creative_writing":1404.7365646711344,"arena_creative_writing_rank":102,"arena_creative_writing_rating_lower":1391.4905429408939,"arena_creative_writing_rating_upper":1417.9825864013746,"arena_creative_writing_vote_count":1960,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3-flash-preview:flex","name":"Google: Gemini 3 Flash Preview (flex)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":0,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tool_choice","tools","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":5.947955390334572,"pricing":{"input":0.25,"output":1.5,"cache_read":0.024999999999999998,"cache_write":0.0416666666666667},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3-flash-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-12-17","knowledge_cutoff":"2025-01","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1194,"win_rate":57,"rank":67},"arena_text":1472.7953716618217,"arena_text_rank":44,"arena_text_rating_lower":1468.45319359402,"arena_text_rating_upper":1477.1375497296233,"arena_text_vote_count":31325,"arena_text_date":"2026-10-15","arena_creative_writing":1456.8396177111256,"arena_creative_writing_rank":31,"arena_creative_writing_rating_lower":1447.5575944472062,"arena_creative_writing_rating_upper":1466.1216409750452,"arena_creative_writing_vote_count":4830,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.5,"output":3,"cache_read":0.049999999999999996,"cache_write":0.0833333333333333},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3-flash-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2025-12-17","knowledge_cutoff":"2025-01","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":17.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1194,"win_rate":57,"rank":67},"arena_text":1472.7953716618217,"arena_text_rank":44,"arena_text_rating_lower":1468.45319359402,"arena_text_rating_upper":1477.1375497296233,"arena_text_vote_count":31325,"arena_text_date":"2026-10-15","arena_creative_writing":1456.8396177111256,"arena_creative_writing_rank":31,"arena_creative_writing_rating_lower":1447.5575944472062,"arena_creative_writing_rating_upper":1466.1216409750452,"arena_creative_writing_vote_count":4830,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3-flash-preview:priority","name":"Google: Gemini 3 Flash Preview (priority)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tool_choice","tools","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.8999999999999999,"output":5.4,"cache_read":0.09,"cache_write":0.15},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3-flash-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-12-17","knowledge_cutoff":"2025-01","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1194,"win_rate":57,"rank":67},"arena_text":1472.7953716618217,"arena_text_rank":44,"arena_text_rating_lower":1468.45319359402,"arena_text_rating_upper":1477.1375497296233,"arena_text_vote_count":31325,"arena_text_date":"2026-10-15","arena_creative_writing":1456.8396177111256,"arena_creative_writing_rank":31,"arena_creative_writing_rating_lower":1447.5575944472062,"arena_creative_writing_rating_upper":1466.1216409750452,"arena_creative_writing_vote_count":4830,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-3-flash-preview:batch","name":"Google: Gemini 3 Flash Preview (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","response_format","tool_choice","tools","stop","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.25,"output":1.5,"cache_read":0.05,"cache_write":null},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3-flash-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-12-17","knowledge_cutoff":"2025-01","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1194,"win_rate":57,"rank":67},"arena_text":1472.7953716618217,"arena_text_rank":44,"arena_text_rating_lower":1468.45319359402,"arena_text_rating_upper":1477.1375497296233,"arena_text_vote_count":31325,"arena_text_date":"2026-10-15","arena_creative_writing":1456.8396177111256,"arena_creative_writing_rank":31,"arena_creative_writing_rating_lower":1447.5575944472062,"arena_creative_writing_rating_upper":1466.1216409750452,"arena_creative_writing_vote_count":4830,"arena_creative_writing_date":"2026-10-15"}},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","provider":"novita","provider_display":"Novita","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.7134670487106,"pricing":{"input":0.049999999999999996,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"nvidia/nemotron-3-nano-30b-a3b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-12-15","knowledge_cutoff":"2025-06-25","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":14.4,"agentic_index":1,"design_arena_best":null}},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":93.33333333333333,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":96.7930029154519,"pricing":{"input":0.06,"output":0.24,"cache_read":0.012,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-15","knowledge_cutoff":"2025-06-25","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":14.4,"agentic_index":1,"design_arena_best":null}},{"id":"openai/gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":32000,"uptime_30m":null,"supported_parameters":["structured_outputs","response_format","max_completion_tokens","tools","tool_choice","seed","verbosity"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":96000,"uptime_1d":null,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1202,"win_rate":56.1,"rank":61}}},{"id":"openai/gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":21,"output":168,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.2-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.2-pro:batch","name":"OpenAI: GPT-5.2 Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":10.5,"output":84,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.2-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5.2:flex","name":"OpenAI: GPT-5.2 (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.875,"output":7,"cache_read":0.0875,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.2","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":30.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1202,"win_rate":56.1,"rank":61},"arena_text":1435.4042188843448,"arena_text_rank":105,"arena_text_rating_lower":1432.2311055571777,"arena_text_rating_upper":1438.577332211512,"arena_text_vote_count":83855,"arena_text_date":"2026-10-15","arena_creative_writing":1391.3349161561985,"arena_creative_writing_rank":124,"arena_creative_writing_rating_lower":1385.2103091971858,"arena_creative_writing_rating_upper":1397.4595231152111,"arena_creative_writing_vote_count":13925,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.2","name":"OpenAI: GPT-5.2","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_completion_tokens","tools","tool_choice","seed","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.2","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":30.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1202,"win_rate":56.1,"rank":61},"arena_text":1435.4042188843448,"arena_text_rank":105,"arena_text_rating_lower":1432.2311055571777,"arena_text_rating_upper":1438.577332211512,"arena_text_vote_count":83855,"arena_text_date":"2026-10-15","arena_creative_writing":1391.3349161561985,"arena_creative_writing_rank":124,"arena_creative_writing_rating_lower":1385.2103091971858,"arena_creative_writing_rating_upper":1397.4595231152111,"arena_creative_writing_vote_count":13925,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.2","name":"OpenAI: GPT-5.2","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.2","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":30.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1202,"win_rate":56.1,"rank":61},"arena_text":1435.4042188843448,"arena_text_rank":105,"arena_text_rating_lower":1432.2311055571777,"arena_text_rating_upper":1438.577332211512,"arena_text_vote_count":83855,"arena_text_date":"2026-10-15","arena_creative_writing":1391.3349161561985,"arena_creative_writing_rank":124,"arena_creative_writing_rating_lower":1385.2103091971858,"arena_creative_writing_rating_upper":1397.4595231152111,"arena_creative_writing_vote_count":13925,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.2:fast","name":"OpenAI: GPT-5.2 (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":3.5,"output":28,"cache_read":0.35,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.2","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":30.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1202,"win_rate":56.1,"rank":61},"arena_text":1435.4042188843448,"arena_text_rank":105,"arena_text_rating_lower":1432.2311055571777,"arena_text_rating_upper":1438.577332211512,"arena_text_vote_count":83855,"arena_text_date":"2026-10-15","arena_creative_writing":1391.3349161561985,"arena_creative_writing_rank":124,"arena_creative_writing_rating_lower":1385.2103091971858,"arena_creative_writing_rating_upper":1397.4595231152111,"arena_creative_writing_vote_count":13925,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.2:batch","name":"OpenAI: GPT-5.2 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":0.875,"output":7,"cache_read":0.0875,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.2","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":30.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1202,"win_rate":56.1,"rank":61},"arena_text":1435.4042188843448,"arena_text_rank":105,"arena_text_rating_lower":1432.2311055571777,"arena_text_rating_upper":1438.577332211512,"arena_text_vote_count":83855,"arena_text_date":"2026-10-15","arena_creative_writing":1391.3349161561985,"arena_creative_writing_rank":124,"arena_creative_writing_rating_lower":1385.2103091971858,"arena_creative_writing_rating_upper":1397.4595231152111,"arena_creative_writing_vote_count":13925,"arena_creative_writing_date":"2026-10-15"}},{"id":"mistralai/devstral-2512","name":"Mistral: Devstral 2 2512","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":209715,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.39999999999999997,"output":2,"cache_read":0.04,"cache_write":null},"org":"mistral","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"devstral-2512","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"high","source":"models.dev","release_date":"2025-12-09","knowledge_cutoff":"2025-12","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":null,"coding_index":31.3,"agentic_index":2.3,"design_arena_best":null}},{"id":"relace/relace-search","name":"Relace: Relace Search","provider":"relace","provider_display":"Relace","quantization":"bf16","discount":0,"context_length":256000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["tools","tool_choice","response_format","temperature","top_p","stop","seed","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":3,"cache_read":null,"cache_write":null},"org":"relace","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"z-ai/glm-4.6v","name":"Z.ai: GLM 4.6V","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.88623435722411,"pricing":{"input":0.3,"output":0.8999999999999999,"cache_read":0.055,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.6v","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-12-08","knowledge_cutoff":"2025-04","description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":8.4,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1378.2509451177166,"arena_text_rank":191,"arena_text_rating_lower":1367.0800899074904,"arena_text_rating_upper":1389.4218003279427,"arena_text_vote_count":2837,"arena_text_date":"2026-10-15","arena_creative_writing":1350.273181446818,"arena_creative_writing_rank":178,"arena_creative_writing_rating_lower":1322.02309236839,"arena_creative_writing_rating_upper":1378.5232705252456,"arena_creative_writing_vote_count":424,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.6v","name":"Z.ai: GLM 4.6V","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tool_choice","tools","top_k"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":95.51020408163265,"pricing":{"input":0.3,"output":0.8999999999999999,"cache_read":0.049999999999999996,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.6v","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-12-08","knowledge_cutoff":"2025-04","description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":8.4,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1378.2509451177166,"arena_text_rank":191,"arena_text_rating_lower":1367.0800899074904,"arena_text_rating_upper":1389.4218003279427,"arena_text_vote_count":2837,"arena_text_date":"2026-10-15","arena_creative_writing":1350.273181446818,"arena_creative_writing_rank":178,"arena_creative_writing_rating_lower":1322.02309236839,"arena_creative_writing_rating_upper":1378.5232705252456,"arena_creative_writing_vote_count":424,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_completion_tokens","tools","tool_choice","seed","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.1-codex-max","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-11-13","knowledge_cutoff":"2024-09-30","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"amazon/nova-2-lite-v1","name":"Amazon: Nova 2 Lite","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":65535,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tool_choice","tools"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.85955056179775,"pricing":{"input":0.3,"output":2.5,"cache_read":0.075,"cache_write":0.3},"org":"amazon","zdr":true,"modelsdev":{"base_url":null,"model_id":"global.amazon.nova-2-lite-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2025-12-02","knowledge_cutoff":"2025-10","description":"Multimodal reasoning model for visual analysis, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":23,"agentic_index":null,"design_arena_best":null}},{"id":"mistralai/ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":209715,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.07142857142858,"pricing":{"input":0.19999999999999998,"output":0.19999999999999998,"cache_read":0.02,"cache_write":null},"org":"mistral","zdr":true,"modelsdev":{"base_url":null,"model_id":"ministral-14b-2512","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"high","source":"models.dev","release_date":"2025-12-02","knowledge_cutoff":null,"description":"Open vision-language model for efficient local deployment, instruction following, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":14.4,"agentic_index":1.1,"design_arena_best":{"category":"website","elo":1081,"win_rate":44.8,"rank":116}}},{"id":"mistralai/ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":209715,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.15,"cache_read":0.015,"cache_write":null},"org":"mistral","zdr":true,"modelsdev":{"base_url":null,"model_id":"ministral-8b-2512","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"high","source":"models.dev","release_date":"2025-12-02","knowledge_cutoff":null,"description":"Compact open vision-language model for edge deployment, instruction following, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":9.7,"agentic_index":0.6,"design_arena_best":{"category":"website","elo":1063,"win_rate":42.9,"rank":118}}},{"id":"mistralai/ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":104857,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tool_choice","tools"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.09999999999999999,"cache_read":0.01,"cache_write":null},"org":"mistral","zdr":true,"modelsdev":{"base_url":null,"model_id":"ministral-3b-2512","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"high","source":"models.dev","release_date":"2025-12-02","knowledge_cutoff":null,"description":"Compact open vision-language model for edge deployment, instruction following, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":4.8,"agentic_index":0.8,"design_arena_best":{"category":"website","elo":1026,"win_rate":38.2,"rank":129}}},{"id":"mistralai/mistral-large-2512","name":"Mistral: Mistral Large 3 2512","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":209715,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.92897727272727,"pricing":{"input":0.5,"output":1.5,"cache_read":0.049999999999999996,"cache_write":null},"org":"mistral","zdr":true,"modelsdev":{"base_url":null,"model_id":"mistral-large-2512","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"high","source":"models.dev","release_date":"2024-11-01","knowledge_cutoff":"2024-11","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":20.1,"agentic_index":1,"design_arena_best":{"category":"website","elo":1162,"win_rate":49.5,"rank":86}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.28,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":false,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.68055555555556,"pricing":{"input":0.20879999999999999,"output":0.30960000000000004,"cache_read":0.0216,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","response_format","tools","tool_choice","structured_outputs","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.51388888888889,"pricing":{"input":0.25899999999999995,"output":0.7999999999999999,"cache_read":0.14,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"deepseek-ai/DeepSeek-V3.2","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","response_format","tools","tool_choice","seed","logit_bias","stop","min_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.05555555555556,"pricing":{"input":0.26,"output":0.38,"cache_read":0.13,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","stop","seed","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.84984984984985,"pricing":{"input":0.28,"output":0.42,"cache_read":0.028,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":95.41666666666667,"pricing":{"input":0.3,"output":0.96,"cache_read":0.09,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":163840,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","structured_outputs","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.69135802469135,"pricing":{"input":1,"output":1,"cache_read":0.5,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"mara","provider_display":"Mara","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":7168,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_k","top_p","logprobs","top_logprobs","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":4.5,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16,"coding_index":44.2,"agentic_index":null,"design_arena_best":{"category":"website","elo":1173,"win_rate":50.2,"rank":81},"arena_text":1424.6358414432184,"arena_text_rank":123,"arena_text_rating_lower":1421.1447741191487,"arena_text_rating_upper":1428.1269087672881,"arena_text_vote_count":48112,"arena_text_date":"2026-10-15","arena_creative_writing":1400.205997446263,"arena_creative_writing_rank":110,"arena_creative_writing_rating_lower":1392.5704574733825,"arena_creative_writing_rating_upper":1407.8415374191432,"arena_creative_writing_vote_count":6883,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1245,"win_rate":59.7,"rank":47}}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","max_completion_tokens","tools","tool_choice","response_format","verbosity"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1245,"win_rate":59.7,"rank":47}}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","tool_choice","tools","verbosity","structured_outputs","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1245,"win_rate":59.7,"rank":47}}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_k","stop","tool_choice","tools","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1245,"win_rate":59.7,"rank":47}}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1245,"win_rate":59.7,"rank":47}}},{"id":"anthropic/claude-opus-4.5:batch","name":"Anthropic: Claude Opus 4.5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","tool_choice","tools","structured_outputs","response_format","verbosity"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1245,"win_rate":59.7,"rank":47}}},{"id":"openai/gpt-5.1:flex","name":"OpenAI: GPT-5.1 (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.625,"output":5,"cache_read":0.0625,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.1","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-11-13","knowledge_cutoff":"2024-09-30","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.7,"coding_index":49.4,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1204,"win_rate":58,"rank":58},"arena_text":1438.6083170544998,"arena_text_rank":99,"arena_text_rating_lower":1435.0172736066443,"arena_text_rating_upper":1442.1993605023551,"arena_text_vote_count":44434,"arena_text_date":"2026-10-15","arena_creative_writing":1408.3845238852498,"arena_creative_writing_rank":94,"arena_creative_writing_rating_lower":1400.487512223651,"arena_creative_writing_rating_upper":1416.2815355468483,"arena_creative_writing_vote_count":6669,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.1","name":"OpenAI: GPT-5.1","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_completion_tokens","tools","tool_choice","seed","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.25,"output":10,"cache_read":0.13,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.1","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-11-14","knowledge_cutoff":"2024-09-30","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.7,"coding_index":49.4,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1204,"win_rate":58,"rank":58},"arena_text":1438.6083170544998,"arena_text_rank":99,"arena_text_rating_lower":1435.0172736066443,"arena_text_rating_upper":1442.1993605023551,"arena_text_vote_count":44434,"arena_text_date":"2026-10-15","arena_creative_writing":1408.3845238852498,"arena_creative_writing_rank":94,"arena_creative_writing_rating_lower":1400.487512223651,"arena_creative_writing_rating_upper":1416.2815355468483,"arena_creative_writing_vote_count":6669,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.1","name":"OpenAI: GPT-5.1","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.1","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-11-13","knowledge_cutoff":"2024-09-30","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.7,"coding_index":49.4,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1204,"win_rate":58,"rank":58},"arena_text":1438.6083170544998,"arena_text_rank":99,"arena_text_rating_lower":1435.0172736066443,"arena_text_rating_upper":1442.1993605023551,"arena_text_vote_count":44434,"arena_text_date":"2026-10-15","arena_creative_writing":1408.3845238852498,"arena_creative_writing_rank":94,"arena_creative_writing_rating_lower":1400.487512223651,"arena_creative_writing_rating_upper":1416.2815355468483,"arena_creative_writing_vote_count":6669,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.1:fast","name":"OpenAI: GPT-5.1 (fast)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":2.5,"output":20,"cache_read":0.25,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.1","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-11-13","knowledge_cutoff":"2024-09-30","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.7,"coding_index":49.4,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1204,"win_rate":58,"rank":58},"arena_text":1438.6083170544998,"arena_text_rank":99,"arena_text_rating_lower":1435.0172736066443,"arena_text_rating_upper":1442.1993605023551,"arena_text_vote_count":44434,"arena_text_date":"2026-10-15","arena_creative_writing":1408.3845238852498,"arena_creative_writing_rank":94,"arena_creative_writing_rating_lower":1400.487512223651,"arena_creative_writing_rating_upper":1416.2815355468483,"arena_creative_writing_vote_count":6669,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.1:batch","name":"OpenAI: GPT-5.1 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":0.625,"output":5,"cache_read":0.0625,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.1","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-11-13","knowledge_cutoff":"2024-09-30","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":24.7,"coding_index":49.4,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1204,"win_rate":58,"rank":58},"arena_text":1438.6083170544998,"arena_text_rank":99,"arena_text_rating_lower":1435.0172736066443,"arena_text_rating_upper":1442.1993605023551,"arena_text_vote_count":44434,"arena_text_date":"2026-10-15","arena_creative_writing":1408.3845238852498,"arena_creative_writing_rank":94,"arena_creative_writing_rating_lower":1400.487512223651,"arena_creative_writing_rating_upper":1416.2815355468483,"arena_creative_writing_vote_count":6669,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5.1-codex","name":"OpenAI: GPT-5.1-Codex","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_completion_tokens","tools","tool_choice","seed","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.25,"output":10,"cache_read":0.13,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.1-codex","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-11-14","knowledge_cutoff":"2024-09-30","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1232,"win_rate":60,"rank":47}}},{"id":"openai/gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1-Codex-Mini","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_completion_tokens","tools","tool_choice","seed","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.25,"output":2,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.1-codex-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-11-14","knowledge_cutoff":"2024-09-30","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1109,"win_rate":42.9,"rank":109}}},{"id":"moonshotai/kimi-k2-thinking","name":"MoonshotAI: Kimi K2 Thinking","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":98304,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6,"output":2.5,"cache_read":0.15,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"moonshotai/kimi-k2-thinking","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-11-06","knowledge_cutoff":"2024-08","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"modified-mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":22,"coding_index":21,"agentic_index":null,"design_arena_best":{"category":"website","elo":1111,"win_rate":48.8,"rank":108},"arena_text":1430.0979685766106,"arena_text_rank":116,"arena_text_rating_lower":1427.01038052258,"arena_text_rating_upper":1433.185556630641,"arena_text_vote_count":63368,"arena_text_date":"2026-10-15","arena_creative_writing":1391.2119431696153,"arena_creative_writing_rank":126,"arena_creative_writing_rating_lower":1384.6191198043907,"arena_creative_writing_rating_upper":1397.8047665348402,"arena_creative_writing_vote_count":9534,"arena_creative_writing_date":"2026-10-15"}},{"id":"amazon/nova-premier-v1","name":"Amazon: Nova Premier 1.0","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":32000,"uptime_30m":0,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":0,"pricing":{"input":2.5,"output":12.5,"cache_read":0.625,"cache_write":2.5},"org":"amazon","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"us.amazon.nova-premier-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2025-04-30","knowledge_cutoff":"2024-10","description":"Multimodal model for complex analysis, long-context understanding, tool use, and model distillation","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":835,"win_rate":26.2,"rank":145}}},{"id":"perplexity/sonar-pro-search","name":"Perplexity: Sonar Pro Search","provider":"perplexity","provider_display":"Perplexity","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":8000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":null,"cache_write":null},"org":"perplexity","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"mistralai/voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":26214,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.85734664764621,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.01,"cache_write":null},"org":"mistral","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-15","knowledge_cutoff":null,"description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Apache 2.0","context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":null},"org":"openai","zdr":true,"lifecycle_status":"beta","modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-safeguard-20b","doc_url":"https://console.groq.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-10-29","knowledge_cutoff":null,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null},{"id":"minimax/minimax-m2","name":"MiniMax: MiniMax M2","provider":"minimax","provider_display":"Minimax","quantization":"fp8","discount":0.15,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tool_choice","tools"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.255,"output":1.02,"cache_read":null,"cache_write":null},"org":"minimax","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-27","knowledge_cutoff":null,"description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1141,"win_rate":48,"rank":99},"arena_text":1343.3349893374027,"arena_text_rank":227,"arena_text_rating_lower":1335.5942275820846,"arena_text_rating_upper":1351.0757510927206,"arena_text_vote_count":6856,"arena_text_date":"2026-10-15","arena_creative_writing":1282.9844870241016,"arena_creative_writing_rank":261,"arena_creative_writing_rating_lower":1262.5092499333787,"arena_creative_writing_rating_upper":1303.4597241148242,"arena_creative_writing_vote_count":897,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","top_k","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.9,"agentic_index":8,"design_arena_best":{"category":"asciiart","elo":1137,"win_rate":49.3,"rank":51}}},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.9,"agentic_index":8,"design_arena_best":{"category":"asciiart","elo":1137,"win_rate":49.3,"rank":51}}},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","structured_outputs","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.84790874524715,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.9,"agentic_index":8,"design_arena_best":{"category":"asciiart","elo":1137,"win_rate":49.3,"rank":51}}},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.9,"agentic_index":8,"design_arena_best":{"category":"asciiart","elo":1137,"win_rate":49.3,"rank":51}}},{"id":"anthropic/claude-haiku-4.5:batch","name":"Anthropic: Claude Haiku 4.5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.5,"output":2.5,"cache_read":0.049999999999999996,"cache_write":0.625},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.9,"agentic_index":8,"design_arena_best":{"category":"asciiart","elo":1137,"win_rate":49.3,"rank":51}}},{"id":"qwen/qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.9297259311314,"pricing":{"input":0.25,"output":0.75,"cache_read":0.12,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-15","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":7.3,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.29,"output":1,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3-VL-30B-A3B-Thinking","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-10-11","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":94.0677966101695,"pricing":{"input":0.19999999999999998,"output":0.7,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3-vl-30b-a3b-instruct","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-10-04","knowledge_cutoff":null,"description":"Open vision-language MoE model for image and video understanding, documents, and visual agents","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":7.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":62.857142857142854,"pricing":{"input":0.29,"output":1,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-10-04","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":7.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"openai/gpt-5-pro","name":"OpenAI: GPT-5 Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":15,"output":120,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-10-06","knowledge_cutoff":"2024-09-30","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-5-pro:batch","name":"OpenAI: GPT-5 Pro (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":7.5,"output":60,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-10-06","knowledge_cutoff":"2024-09-30","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"z-ai/glm-4.6:flex","name":"Z.ai: GLM 4.6 (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.39999999999999997,"output":1.5999999999999999,"cache_read":0.08,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":null,"model_id":"zai-org/GLM-4.6","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-09-30","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":14.9,"coding_index":45.8,"agentic_index":null,"design_arena_best":{"category":"godotgamedev","elo":1180,"win_rate":53.2,"rank":17},"arena_text":1424.1228406450284,"arena_text_rank":125,"arena_text_rating_lower":1420.2224633968601,"arena_text_rating_upper":1428.0232178931967,"arena_text_vote_count":35824,"arena_text_date":"2026-10-15","arena_creative_writing":1400.5550945178709,"arena_creative_writing_rank":109,"arena_creative_writing_rating_lower":1392.044388175411,"arena_creative_writing_rating_upper":1409.0658008603307,"arena_creative_writing_vote_count":5145,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.6","name":"Z.ai: GLM 4.6","provider":"venice","provider_display":"Venice","quantization":"fp4","discount":0,"context_length":198000,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.44179651695693,"pricing":{"input":0.43,"output":1.75,"cache_read":0.08,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"zai-org-glm-4.6","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2025-09-30","knowledge_cutoff":"2025-04","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":14.9,"coding_index":45.8,"agentic_index":null,"design_arena_best":{"category":"godotgamedev","elo":1180,"win_rate":53.2,"rank":17},"arena_text":1424.1228406450284,"arena_text_rank":125,"arena_text_rating_lower":1420.2224633968601,"arena_text_rating_upper":1428.0232178931967,"arena_text_vote_count":35824,"arena_text_date":"2026-10-15","arena_creative_writing":1400.5550945178709,"arena_creative_writing_rank":109,"arena_creative_writing_rating_lower":1392.044388175411,"arena_creative_writing_rating_upper":1409.0658008603307,"arena_creative_writing_vote_count":5145,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.6","name":"Z.ai: GLM 4.6","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.55,"output":2.2,"cache_read":0.11,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.6","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-09-30","knowledge_cutoff":"2025-04","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":14.9,"coding_index":45.8,"agentic_index":null,"design_arena_best":{"category":"godotgamedev","elo":1180,"win_rate":53.2,"rank":17},"arena_text":1424.1228406450284,"arena_text_rank":125,"arena_text_rating_lower":1420.2224633968601,"arena_text_rating_upper":1428.0232178931967,"arena_text_vote_count":35824,"arena_text_date":"2026-10-15","arena_creative_writing":1400.5550945178709,"arena_creative_writing_rank":109,"arena_creative_writing_rating_lower":1392.044388175411,"arena_creative_writing_rating_upper":1409.0658008603307,"arena_creative_writing_vote_count":5145,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.6","name":"Z.ai: GLM 4.6","provider":"z-ai","provider_display":"Z.AI","quantization":"fp4","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.51338199513383,"pricing":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.6","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-09-30","knowledge_cutoff":"2025-04","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":14.9,"coding_index":45.8,"agentic_index":null,"design_arena_best":{"category":"godotgamedev","elo":1180,"win_rate":53.2,"rank":17},"arena_text":1424.1228406450284,"arena_text_rank":125,"arena_text_rating_lower":1420.2224633968601,"arena_text_rating_upper":1428.0232178931967,"arena_text_vote_count":35824,"arena_text_date":"2026-10-15","arena_creative_writing":1400.5550945178709,"arena_creative_writing_rank":109,"arena_creative_writing_rating_lower":1392.044388175411,"arena_creative_writing_rating_upper":1409.0658008603307,"arena_creative_writing_vote_count":5145,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tool_choice","tools","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":52.1,"agentic_index":15.8,"design_arena_best":{"category":"asciiart","elo":1202,"win_rate":56.1,"rank":25}}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","max_completion_tokens","tools","tool_choice","top_k","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":52.1,"agentic_index":15.8,"design_arena_best":{"category":"asciiart","elo":1202,"win_rate":56.1,"rank":25}}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":52.1,"agentic_index":15.8,"design_arena_best":{"category":"asciiart","elo":1202,"win_rate":56.1,"rank":25}}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":52.1,"agentic_index":15.8,"design_arena_best":{"category":"asciiart","elo":1202,"win_rate":56.1,"rank":25}}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","structured_outputs","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":52.1,"agentic_index":15.8,"design_arena_best":{"category":"asciiart","elo":1202,"win_rate":56.1,"rank":25}}},{"id":"anthropic/claude-sonnet-4.5:batch","name":"Anthropic: Claude Sonnet 4.5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1.5,"output":7.5,"cache_read":0.15,"cache_write":1.875},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":52.1,"agentic_index":15.8,"design_arena_best":{"category":"asciiart","elo":1202,"win_rate":56.1,"rank":25}}},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.375,"pricing":{"input":0.27,"output":0.41,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"deepseek-ai/DeepSeek-V3.2-Exp","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-10-10","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1177,"win_rate":54.3,"rank":77},"arena_text":1421.6981589625707,"arena_text_rank":129,"arena_text_rating_lower":1415.321567134356,"arena_text_rating_upper":1428.0747507907854,"arena_text_vote_count":12004,"arena_text_date":"2026-10-15","arena_creative_writing":1409.1549276870815,"arena_creative_writing_rank":93,"arena_creative_writing_rating_lower":1394.5935184279015,"arena_creative_writing_rating_upper":1423.7163369462612,"arena_creative_writing_vote_count":1665,"arena_creative_writing_date":"2026-10-15"}},{"id":"thedrummer/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93041057759221,"pricing":{"input":0.3,"output":0.5,"cache_read":0.15,"cache_write":null},"org":"thedrummer","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"relace/relace-apply-3","name":"Relace: Relace Apply 3","provider":"relace","provider_display":"Relace","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["stop","seed","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.85,"output":1.25,"cache_read":null,"cache_write":null},"org":"relace","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":90,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":96.80555555555556,"pricing":{"input":0.21,"output":1.9,"cache_read":0.09999999999999999,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-23","knowledge_cutoff":"2025-03-31","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1413.3151783944136,"arena_text_rank":146,"arena_text_rating_lower":1406.7915427149521,"arena_text_rating_upper":1419.8388140738748,"arena_text_vote_count":11320,"arena_text_date":"2026-10-15","arena_creative_writing":1356.5721800790488,"arena_creative_writing_rank":172,"arena_creative_writing_rating_lower":1339.6991843255719,"arena_creative_writing_rating_upper":1373.4451758325256,"arena_creative_writing_vote_count":1356,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.21,"output":1.9,"cache_read":0.09999999999999999,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-23","knowledge_cutoff":"2025-03-31","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://deepinfra.com/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1413.3151783944136,"arena_text_rank":146,"arena_text_rating_lower":1406.7915427149521,"arena_text_rating_upper":1419.8388140738748,"arena_text_vote_count":11320,"arena_text_date":"2026-10-15","arena_creative_writing":1356.5721800790488,"arena_creative_writing_rank":172,"arena_creative_writing_rating_lower":1339.6991843255719,"arena_creative_writing_rating_upper":1373.4451758325256,"arena_creative_writing_vote_count":1356,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.27,"output":1,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"deepseek-ai/DeepSeek-V3.1-Terminus","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-09-29","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":43.5,"agentic_index":6.8,"design_arena_best":{"category":"website","elo":1185,"win_rate":56.4,"rank":73},"arena_text":1414.6891098049177,"arena_text_rank":141,"arena_text_rating_lower":1404.9718876785898,"arena_text_rating_upper":1424.4063319312456,"arena_text_vote_count":3608,"arena_text_date":"2026-10-15","arena_creative_writing":1404.1051785530278,"arena_creative_writing_rank":103,"arena_creative_writing_rating_lower":1376.8926909298336,"arena_creative_writing_rating_upper":1431.3176661762218,"arena_creative_writing_vote_count":447,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":997952,"uptime_1d":100,"pricing":{"input":0.195,"output":0.975,"cache_read":0.039,"cache_write":0.24375},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3-coder-flash","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2025-07-28","knowledge_cutoff":"2025-04","description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3-next-80b-a3b-instruct:flex","name":"Qwen: Qwen3 Next 80B A3B Instruct (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.072,"output":0.88,"cache_read":null,"cache_write":null},"org":"qwen","modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-09","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.6,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1398.5312003749314,"arena_text_rank":164,"arena_text_rating_lower":1393.7574764680655,"arena_text_rating_upper":1403.3049242817972,"arena_text_vote_count":22760,"arena_text_date":"2026-10-15","arena_creative_writing":1313.3902317801694,"arena_creative_writing_rank":219,"arena_creative_writing_rating_lower":1302.5039488652117,"arena_creative_writing_rating_upper":1324.2765146951272,"arena_creative_writing_vote_count":3033,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":1.1,"cache_read":0.07,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.6,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1398.5312003749314,"arena_text_rank":164,"arena_text_rating_lower":1393.7574764680655,"arena_text_rating_upper":1403.3049242817972,"arena_text_vote_count":22760,"arena_text_date":"2026-10-15","arena_creative_writing":1313.3902317801694,"arena_creative_writing_rank":219,"arena_creative_writing_rating_lower":1302.5039488652117,"arena_creative_writing_rating_upper":1324.2765146951272,"arena_creative_writing_vote_count":3033,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3-next-80b-a3b-instruct:priority","name":"Qwen: Qwen3 Next 80B A3B Instruct (priority)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.135,"output":1.6500000000000001,"cache_read":null,"cache_write":null},"org":"qwen","modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-09","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.6,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1398.5312003749314,"arena_text_rank":164,"arena_text_rating_lower":1393.7574764680655,"arena_text_rating_upper":1403.3049242817972,"arena_text_vote_count":22760,"arena_text_date":"2026-10-15","arena_creative_writing":1313.3902317801694,"arena_creative_writing_rank":219,"arena_creative_writing_rating_lower":1302.5039488652117,"arena_creative_writing_rating_upper":1324.2765146951272,"arena_creative_writing_vote_count":3033,"arena_creative_writing_date":"2026-10-15"}},{"id":"moonshotai/kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":98304,"uptime_30m":100,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6,"output":2.5,"cache_read":null,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"moonshotai/kimi-k2-0905","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-09-05","knowledge_cutoff":null,"description":"September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Modified MIT","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1107,"win_rate":48.3,"rank":110},"arena_text":1418.6124049646044,"arena_text_rank":132,"arena_text_rating_lower":1412.0867538211378,"arena_text_rating_upper":1425.1380561080712,"arena_text_vote_count":11589,"arena_text_date":"2026-10-15","arena_creative_writing":1382.5654549938001,"arena_creative_writing_rank":140,"arena_creative_writing_rating_lower":1367.2194239327805,"arena_creative_writing_rating_upper":1397.9114860548195,"arena_creative_writing_vote_count":1482,"arena_creative_writing_date":"2026-10-15"}},{"id":"nousresearch/hermes-4-405b","name":"Nous: Hermes 4 405B","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","top_k","logprobs","top_logprobs","repetition_penalty","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":120000,"uptime_1d":99.47526236881559,"pricing":{"input":1,"output":3,"cache_read":0.19999999999999998,"cache_write":null},"org":"nous","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"NousResearch/Hermes-4-405B","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2025-08-26","knowledge_cutoff":"2024-08-31","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","structured_outputs","logit_bias","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.25,"output":0.95,"cache_read":0.13,"cache_write":null},"org":"deepseek","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1122,"win_rate":48,"rank":104}}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":98.14385150812065,"pricing":{"input":0.27,"output":1,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1122,"win_rate":48,"rank":104}}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":161000,"max_completion_tokens":144900,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.55,"output":1.6500000000000001,"cache_read":0.55,"cache_write":null},"org":"deepseek","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1122,"win_rate":48,"rank":104}}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"mara","provider_display":"Mara","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":93.33333333333333,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_k","top_p","response_format","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":96.93732193732194,"pricing":{"input":0.6,"output":1.7,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1122,"win_rate":48,"rank":104}}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"sambanova","provider_display":"SambaNova","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":7168,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":92.10526315789474,"pricing":{"input":0.65,"output":1.5,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1122,"win_rate":48,"rank":104}}},{"id":"mistralai/mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":104857,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.39999999999999997,"output":2,"cache_read":0.04,"cache_write":null},"org":"mistral","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.2,"coding_index":20.5,"agentic_index":1.9,"design_arena_best":{"category":"dataviz","elo":1144,"win_rate":47.2,"rank":84}}},{"id":"z-ai/glm-4.5v","name":"Z.ai: GLM 4.5V","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":65536,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.6,"output":1.7999999999999998,"cache_read":0.11,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.5v","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-08-11","knowledge_cutoff":"2025-04","description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1352.1730669993844,"arena_text_rank":214,"arena_text_rating_lower":1343.73602737484,"arena_text_rating_upper":1360.6101066239291,"arena_text_vote_count":4821,"arena_text_date":"2026-10-15","arena_creative_writing":1309.0565236738944,"arena_creative_writing_rank":224,"arena_creative_writing_rating_lower":1286.060020401175,"arena_creative_writing_rating_upper":1332.053026946614,"arena_creative_writing_vote_count":614,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.5v","name":"Z.ai: GLM 4.5V","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":65536,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.36305732484077,"pricing":{"input":0.6,"output":1.7999999999999998,"cache_read":0.11,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.5v","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-08-11","knowledge_cutoff":"2025-04","description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1352.1730669993844,"arena_text_rank":214,"arena_text_rating_lower":1343.73602737484,"arena_text_rating_upper":1360.6101066239291,"arena_text_vote_count":4821,"arena_text_date":"2026-10-15","arena_creative_writing":1309.0565236738944,"arena_creative_writing_rank":224,"arena_creative_writing_rating_lower":1286.060020401175,"arena_creative_writing_rating_upper":1332.053026946614,"arena_creative_writing_vote_count":614,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5","name":"OpenAI: GPT-5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_completion_tokens","tools","tool_choice","seed","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-09-30","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23,"coding_index":37.8,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1221,"win_rate":60.5,"rank":52},"arena_text":1434.8035075319092,"arena_text_rank":106,"arena_text_rating_lower":1430.298651716069,"arena_text_rating_upper":1439.3083633477495,"arena_text_vote_count":31722,"arena_text_date":"2026-10-15","arena_creative_writing":1372.3598223621402,"arena_creative_writing_rank":154,"arena_creative_writing_rating_lower":1362.6621897180087,"arena_creative_writing_rating_upper":1382.0574550062715,"arena_creative_writing_vote_count":4242,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5","name":"OpenAI: GPT-5","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-09-30","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23,"coding_index":37.8,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1221,"win_rate":60.5,"rank":52},"arena_text":1434.8035075319092,"arena_text_rank":106,"arena_text_rating_lower":1430.298651716069,"arena_text_rating_upper":1439.3083633477495,"arena_text_vote_count":31722,"arena_text_date":"2026-10-15","arena_creative_writing":1372.3598223621402,"arena_creative_writing_rank":154,"arena_creative_writing_rating_lower":1362.6621897180087,"arena_creative_writing_rating_upper":1382.0574550062715,"arena_creative_writing_vote_count":4242,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5:batch","name":"OpenAI: GPT-5 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":0.625,"output":5,"cache_read":0.0625,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-09-30","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":23,"coding_index":37.8,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1221,"win_rate":60.5,"rank":52},"arena_text":1434.8035075319092,"arena_text_rank":106,"arena_text_rating_lower":1430.298651716069,"arena_text_rating_upper":1439.3083633477495,"arena_text_vote_count":31722,"arena_text_date":"2026-10-15","arena_creative_writing":1372.3598223621402,"arena_creative_writing_rank":154,"arena_creative_writing_rating_lower":1362.6621897180087,"arena_creative_writing_rating_upper":1382.0574550062715,"arena_creative_writing_vote_count":4242,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5-mini:flex","name":"OpenAI: GPT-5 Mini (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.125,"output":1,"cache_read":0.012499999999999999,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16.8,"coding_index":15.6,"agentic_index":6.8,"design_arena_best":{"category":"dataviz","elo":1131,"win_rate":43.7,"rank":91},"arena_text":1389.9554783950398,"arena_text_rank":177,"arena_text_rating_lower":1385.3073419786917,"arena_text_rating_upper":1394.6036148113878,"arena_text_vote_count":26804,"arena_text_date":"2026-10-15","arena_creative_writing":1323.3899818707955,"arena_creative_writing_rank":209,"arena_creative_writing_rating_lower":1312.973857122176,"arena_creative_writing_rating_upper":1333.806106619415,"arena_creative_writing_vote_count":3520,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":360000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":99.86101459346769,"pricing":{"input":0.25,"output":2,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16.8,"coding_index":15.6,"agentic_index":6.8,"design_arena_best":{"category":"dataviz","elo":1131,"win_rate":43.7,"rank":91},"arena_text":1389.9554783950398,"arena_text_rank":177,"arena_text_rating_lower":1385.3073419786917,"arena_text_rating_upper":1394.6036148113878,"arena_text_vote_count":26804,"arena_text_date":"2026-10-15","arena_creative_writing":1323.3899818707955,"arena_creative_writing_rank":209,"arena_creative_writing_rating_lower":1312.973857122176,"arena_creative_writing_rating_upper":1333.806106619415,"arena_creative_writing_vote_count":3520,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.25,"output":2,"cache_read":0.024999999999999998,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16.8,"coding_index":15.6,"agentic_index":6.8,"design_arena_best":{"category":"dataviz","elo":1131,"win_rate":43.7,"rank":91},"arena_text":1389.9554783950398,"arena_text_rank":177,"arena_text_rating_lower":1385.3073419786917,"arena_text_rating_upper":1394.6036148113878,"arena_text_vote_count":26804,"arena_text_date":"2026-10-15","arena_creative_writing":1323.3899818707955,"arena_creative_writing_rank":209,"arena_creative_writing_rating_lower":1312.973857122176,"arena_creative_writing_rating_upper":1333.806106619415,"arena_creative_writing_vote_count":3520,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5-mini:batch","name":"OpenAI: GPT-5 Mini (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":0.125,"output":1,"cache_read":0.012499999999999999,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16.8,"coding_index":15.6,"agentic_index":6.8,"design_arena_best":{"category":"dataviz","elo":1131,"win_rate":43.7,"rank":91},"arena_text":1389.9554783950398,"arena_text_rank":177,"arena_text_rating_lower":1385.3073419786917,"arena_text_rating_upper":1394.6036148113878,"arena_text_vote_count":26804,"arena_text_date":"2026-10-15","arena_creative_writing":1323.3899818707955,"arena_creative_writing_rank":209,"arena_creative_writing_rating_lower":1312.973857122176,"arena_creative_writing_rating_upper":1333.806106619415,"arena_creative_writing_vote_count":3520,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5-nano:flex","name":"OpenAI: GPT-5 Nano (flex)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.024999999999999998,"output":0.19999999999999998,"cache_read":0.0025,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1101,"win_rate":48.9,"rank":111},"arena_text":1337.7094937450508,"arena_text_rank":236,"arena_text_rating_lower":1330.790540839154,"arena_text_rating_upper":1344.628446650948,"arena_text_vote_count":8132,"arena_text_date":"2026-10-15","arena_creative_writing":1246.4321805318204,"arena_creative_writing_rank":297,"arena_creative_writing_rating_lower":1226.4319209090352,"arena_creative_writing_rating_upper":1266.4324401546055,"arena_creative_writing_vote_count":911,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":360000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_completion_tokens","tools","tool_choice","seed","response_format","structured_outputs","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":99.92779783393502,"pricing":{"input":0.049999999999999996,"output":0.39999999999999997,"cache_read":0.01,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5-nano","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1101,"win_rate":48.9,"rank":111},"arena_text":1337.7094937450508,"arena_text_rank":236,"arena_text_rating_lower":1330.790540839154,"arena_text_rating_upper":1344.628446650948,"arena_text_vote_count":8132,"arena_text_date":"2026-10-15","arena_creative_writing":1246.4321805318204,"arena_creative_writing_rank":297,"arena_creative_writing_rating_lower":1226.4319209090352,"arena_creative_writing_rating_upper":1266.4324401546055,"arena_creative_writing_vote_count":911,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":100,"pricing":{"input":0.049999999999999996,"output":0.39999999999999997,"cache_read":0.005,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1101,"win_rate":48.9,"rank":111},"arena_text":1337.7094937450508,"arena_text_rank":236,"arena_text_rating_lower":1330.790540839154,"arena_text_rating_upper":1344.628446650948,"arena_text_vote_count":8132,"arena_text_date":"2026-10-15","arena_creative_writing":1246.4321805318204,"arena_creative_writing_rank":297,"arena_creative_writing_rating_lower":1226.4319209090352,"arena_creative_writing_rating_upper":1266.4324401546055,"arena_creative_writing_vote_count":911,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-5-nano:batch","name":"OpenAI: GPT-5 Nano (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice","verbosity","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":272000,"uptime_1d":null,"pricing":{"input":0.024999999999999998,"output":0.19999999999999998,"cache_read":0.0025,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1101,"win_rate":48.9,"rank":111},"arena_text":1337.7094937450508,"arena_text_rank":236,"arena_text_rating_lower":1330.790540839154,"arena_text_rating_upper":1344.628446650948,"arena_text_vote_count":8132,"arena_text_date":"2026-10-15","arena_creative_writing":1246.4321805318204,"arena_creative_writing_rank":297,"arena_creative_writing_rating_lower":1226.4319209090352,"arena_creative_writing_rating_upper":1266.4324401546055,"arena_creative_writing_vote_count":911,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"near-ai","provider_display":"Near AI","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","max_tokens","stop","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.03,"output":0.15,"cache_read":0.015,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"venice","provider_display":"Venice","quantization":"int4","discount":0,"context_length":128000,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.86111111111111,"pricing":{"input":0.03,"output":0.15,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai-gpt-oss-120b","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.03,"output":0.16999999999999998,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"dekallm","provider_display":"DekaLLM","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logit_bias","max_tokens","presence_penalty","seed","stop","temperature","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.03,"output":0.18,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"akashml","provider_display":"AkashML","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","seed","frequency_penalty","presence_penalty","repetition_penalty","max_tokens","response_format","structured_outputs","tools","logprobs","top_logprobs","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.03,"output":0.187,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"crusoe","provider_display":"Crusoe","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","min_p","repetition_penalty","top_k","logit_bias","structured_outputs","response_format","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.049999999999999996,"output":0.25,"cache_read":0.049999999999999996,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://api.inference.crusoecloud.com/v1","model_id":"openai/gpt-oss-120b","doc_url":"https://docs.crusoecloud.com/managed-inference/overview","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","response_format","logprobs","top_logprobs","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.65277777777779,"pricing":{"input":0.049999999999999996,"output":0.25,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"novita","provider_display":"Novita","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.72202918693537,"pricing":{"input":0.049999999999999996,"output":0.25,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"openai/gpt-oss-120b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"sail-research","provider_display":"Sail Research","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","max_tokens","presence_penalty","seed","stop","temperature","top_k","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.06,"output":0.39999999999999997,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":4096,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","max_tokens","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.06,"output":0.42,"cache_read":0.012,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"openai-gpt-oss-120b","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"medium","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":0,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","repetition_penalty","top_k","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":1.4613778705636742,"pricing":{"input":0.09,"output":0.36,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"baseten","provider_display":"BaseTen","quantization":"fp4","discount":0,"context_length":128072,"max_completion_tokens":115264,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.09999999999999999,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"openai/gpt-oss-120b","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"parasail","provider_display":"Parasail","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.75,"cache_read":0.055,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai.gpt-oss-120b","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"nebius","provider_display":"Nebius","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","repetition_penalty","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":124000,"uptime_1d":100,"pricing":{"input":0.15,"output":0.6,"cache_read":0.09999999999999999,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"openai/gpt-oss-120b","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","max_tokens","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":87.60504201680672,"pricing":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"openai/gpt-oss-120b","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.74293059125964,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","repetition_penalty","logit_bias","min_p","tools","tool_choice","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":98.25145711906744,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-120b","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-120b","doc_url":"https://console.groq.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"mara","provider_display":"Mara","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":90.9090909090909,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","top_k","top_p","tool_choice","tools","structured_outputs","response_format","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":97.42647058823529,"pricing":{"input":0.15,"output":0.75,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://inference-docs.cerebras.ai/models/overview","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"cerebras","provider_display":"Cerebras","quantization":"fp16","discount":0,"context_length":131072,"max_completion_tokens":40960,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","logprobs","top_logprobs","tools","tool_choice","response_format","structured_outputs","frequency_penalty","presence_penalty","logit_bias","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.35,"output":0.75,"cache_read":0.35,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-oss-120b","doc_url":"https://inference-docs.cerebras.ai/models/overview","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-120b:batch","name":"OpenAI: gpt-oss-120b (batch)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","structured_outputs","logit_bias","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.0296,"output":0.136,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-120b","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":30.4,"agentic_index":3.7,"design_arena_best":{"category":"gamedev","elo":992,"win_rate":40.5,"rank":124},"arena_text":1351.758607712953,"arena_text_rank":215,"arena_text_rating_lower":1347.3939655717056,"arena_text_rating_upper":1356.1232498542006,"arena_text_vote_count":30206,"arena_text_date":"2026-10-15","arena_creative_writing":1278.9905857170677,"arena_creative_writing_rank":266,"arena_creative_writing_rating_lower":1269.087357109735,"arena_creative_writing_rating_upper":1288.8938143244006,"arena_creative_writing_vote_count":3908,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"darkbloom","provider_display":"Darkbloom","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.018,"output":0.09,"cache_read":0.009,"cache_write":null},"org":"openai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Lower latency Mixture-of-Experts model trained on OpenAI's Harmony response format with reasoning capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"akashml","provider_display":"AkashML","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","stop","seed","frequency_penalty","presence_penalty","repetition_penalty","max_tokens","structured_outputs","response_format","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.02,"output":0.09999999999999999,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Lower latency Mixture-of-Experts model trained on OpenAI's Harmony response format with reasoning capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"dekallm","provider_display":"DekaLLM","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","frequency_penalty","logit_bias","max_tokens","presence_penalty","seed","stop","temperature","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.029,"output":0.14,"cache_read":0.029,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Lower latency Mixture-of-Experts model trained on OpenAI's Harmony response format with reasoning capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.03,"output":0.13,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Lower latency Mixture-of-Experts model trained on OpenAI's Harmony response format with reasoning capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"parasail","provider_display":"Parasail","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.51287404314544,"pricing":{"input":0.03,"output":0.15,"cache_read":0.02,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Lower latency Mixture-of-Experts model trained on OpenAI's Harmony response format with reasoning capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":66.66666666666666,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","max_tokens","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":75.72362278244631,"pricing":{"input":0.04,"output":0.18,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"openai/gpt-oss-20b","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.07,"output":0.15,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai.gpt-oss-20b","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice","structured_outputs","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-20b","doc_url":"https://console.groq.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-oss-20b:batch","name":"OpenAI: gpt-oss-20b (batch)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","structured_outputs","logit_bias","response_format","reasoning_effort"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.024,"output":0.112,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-20b","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":20.7,"agentic_index":1.2,"design_arena_best":{"category":"dataviz","elo":933,"win_rate":39.7,"rank":125},"arena_text":1317.4239729820094,"arena_text_rank":267,"arena_text_rating_lower":1311.0092570097922,"arena_text_rating_upper":1323.8386889542264,"arena_text_vote_count":10419,"arena_text_date":"2026-10-15","arena_creative_writing":1240.4892658038912,"arena_creative_writing_rank":304,"arena_creative_writing_rating_lower":1222.1475724088573,"arena_creative_writing_rating_upper":1258.830959198925,"arena_creative_writing_vote_count":1234,"arena_creative_writing_date":"2026-10-15"}},{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","stop","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"org":"anthropic","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1175,"win_rate":55.3,"rank":79}}},{"id":"anthropic/claude-opus-4.1:batch","name":"Anthropic: Claude Opus 4.1 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","stop","tools","tool_choice","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":7.5,"output":37.5,"cache_read":0.75,"cache_write":9.375},"org":"anthropic","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1175,"win_rate":55.3,"rank":79}}},{"id":"mistralai/codestral-2508","name":"Mistral: Codestral 2508","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":204800,"uptime_30m":100,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","tools","tool_choice","prediction"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":0.8999999999999999,"cache_read":0.03,"cache_write":null},"org":"mistral","zdr":true,"modelsdev":{"base_url":null,"model_id":"codestral-2508","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"high","source":"models.dev","release_date":"2025-07-30","knowledge_cutoff":null,"description":"Mistral code model for low-latency completion, fill-in-the-middle, and code generation","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1017,"win_rate":41.1,"rank":115}}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":93.33333333333333,"supported_parameters":["structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":97.900466562986,"pricing":{"input":0.07,"output":0.28,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-07-31","knowledge_cutoff":"2025-04","description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1087,"win_rate":57.1,"rank":114}}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tool_choice","tools"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.77168949771689,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1087,"win_rate":57.1,"rank":114}}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","provider":"dekallm","provider_display":"DekaLLM","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","presence_penalty","seed","stop","temperature","top_p","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.79166666666667,"pricing":{"input":0.09,"output":0.3,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-28","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://cloud.siliconflow.com/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1382.337590205451,"arena_text_rank":188,"arena_text_rating_lower":1377.433598383406,"arena_text_rating_upper":1387.241582027496,"arena_text_vote_count":23322,"arena_text_date":"2026-10-15","arena_creative_writing":1318.6573599457618,"arena_creative_writing_rank":214,"arena_creative_writing_rating_lower":1307.6490411823029,"arena_creative_writing_rating_upper":1329.6656787092204,"arena_creative_writing_vote_count":2964,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.93050729673384,"pricing":{"input":0.09,"output":0.3,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-07-28","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1382.337590205451,"arena_text_rank":188,"arena_text_rating_lower":1377.433598383406,"arena_text_rating_upper":1387.241582027496,"arena_text_vote_count":23322,"arena_text_date":"2026-10-15","arena_creative_writing":1318.6573599457618,"arena_creative_writing_rank":214,"arena_creative_writing_rating_lower":1307.6490411823029,"arena_creative_writing_rating_upper":1329.6656787092204,"arena_creative_writing_vote_count":2964,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","repetition_penalty"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":262144,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.09999999999999999,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2025-07-28","knowledge_cutoff":"2025-12","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1382.337590205451,"arena_text_rank":188,"arena_text_rating_lower":1377.433598383406,"arena_text_rating_upper":1387.241582027496,"arena_text_vote_count":23322,"arena_text_date":"2026-10-15","arena_creative_writing":1318.6573599457618,"arena_creative_writing_rank":214,"arena_creative_writing_rating_lower":1307.6490411823029,"arena_creative_writing_rating_upper":1329.6656787092204,"arena_creative_writing_vote_count":2964,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.5","name":"Z.ai: GLM 4.5","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":98304,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","max_tokens","temperature","top_p","tools","tool_choice","top_k"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.84202211690362,"pricing":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.5","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-07-28","knowledge_cutoff":"2025-04","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.8,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1168,"win_rate":53.7,"rank":83},"arena_text":1410.7960767851844,"arena_text_rank":150,"arena_text_rating_lower":1405.8737096155037,"arena_text_rating_upper":1415.7184439548648,"arena_text_vote_count":23796,"arena_text_date":"2026-10-15","arena_creative_writing":1372.2591640865946,"arena_creative_writing_rank":155,"arena_creative_writing_rating_lower":1361.3157066060623,"arena_creative_writing_rating_upper":1383.2026215671272,"arena_creative_writing_vote_count":3093,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.5-air","name":"Z.ai: GLM 4.5 Air","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":98304,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.13,"output":0.85,"cache_read":0.024999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.5-air","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-07-28","knowledge_cutoff":"2025-04","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.1,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1186,"win_rate":58.5,"rank":64},"arena_text":1372.982853047627,"arena_text_rank":196,"arena_text_rating_lower":1368.7295054947192,"arena_text_rating_upper":1377.2362006005346,"arena_text_vote_count":30660,"arena_text_date":"2026-10-15","arena_creative_writing":1327.487846165283,"arena_creative_writing_rank":205,"arena_creative_writing_rating_lower":1317.9034997532249,"arena_creative_writing_rating_upper":1337.0721925773407,"arena_creative_writing_vote_count":3999,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.5-air","name":"Z.ai: GLM 4.5 Air","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.14,"output":0.86,"cache_read":null,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"zai-org/GLM-4.5-Air","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-07-28","knowledge_cutoff":"2025-04","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.1,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1186,"win_rate":58.5,"rank":64},"arena_text":1372.982853047627,"arena_text_rank":196,"arena_text_rating_lower":1368.7295054947192,"arena_text_rating_upper":1377.2362006005346,"arena_text_vote_count":30660,"arena_text_date":"2026-10-15","arena_creative_writing":1327.487846165283,"arena_creative_writing_rank":205,"arena_creative_writing_rating_lower":1317.9034997532249,"arena_creative_writing_rating_upper":1337.0721925773407,"arena_creative_writing_vote_count":3999,"arena_creative_writing_date":"2026-10-15"}},{"id":"z-ai/glm-4.5-air","name":"Z.ai: GLM 4.5 Air","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":98304,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.35622317596567,"pricing":{"input":0.19999999999999998,"output":1.1,"cache_read":0.03,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.5-air","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-07-28","knowledge_cutoff":"2025-04","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":11.1,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1186,"win_rate":58.5,"rank":64},"arena_text":1372.982853047627,"arena_text_rank":196,"arena_text_rating_lower":1368.7295054947192,"arena_text_rating_upper":1377.2362006005346,"arena_text_vote_count":30660,"arena_text_date":"2026-10-15","arena_creative_writing":1327.487846165283,"arena_creative_writing_rank":205,"arena_creative_writing_rating_lower":1317.9034997532249,"arena_creative_writing_rating_upper":1337.0721925773407,"arena_creative_writing_vote_count":3999,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.44999999999999996,"output":3.5,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":null,"model_id":"qwen3-235b-a22b-thinking-2507","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2025-07-25","knowledge_cutoff":null,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"Apache 2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":22.1,"agentic_index":1.3,"design_arena_best":{"category":"website","elo":1051,"win_rate":42,"rank":122},"arena_text":1399.756218631016,"arena_text_rank":163,"arena_text_rating_lower":1393.182836429032,"arena_text_rating_upper":1406.329600833,"arena_text_vote_count":8823,"arena_text_date":"2026-10-15","arena_creative_writing":1369.679526890342,"arena_creative_writing_rank":158,"arena_creative_writing_rating_lower":1351.7018858887075,"arena_creative_writing_rating_upper":1387.6571678919768,"arena_creative_writing_vote_count":1084,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B (turbo)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":92.79731993299832,"pricing":{"input":0.3,"output":1,"cache_read":0.09999999999999999,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-07-22","knowledge_cutoff":"2025-04","description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1157,"win_rate":61.7,"rank":91}}},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":82.95302013422818,"pricing":{"input":0.35,"output":1.5,"cache_read":0.04,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":null,"model_id":"qwen3-coder-480b-a35b-instruct-turbo","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2026-01-27","knowledge_cutoff":null,"description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1157,"win_rate":61.7,"rank":91}}},{"id":"bytedance/ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":128000,"max_completion_tokens":2048,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.77675840978594,"pricing":{"input":0.09999999999999999,"output":0.19999999999999998,"cache_read":0.09999999999999999,"cache_write":null},"org":"bytedance","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"google/gemini-2.5-flash-lite:flex","name":"Google: Gemini 2.5 Flash Lite (flex)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.049999999999999996,"output":0.19999999999999998,"cache_read":0.005,"cache_write":0.0416666666666667},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.7,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"google/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.01,"cache_write":0.0833333333333333},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.7,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"google/gemini-2.5-flash-lite:priority","name":"Google: Gemini 2.5 Flash Lite (priority)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.2721979621543,"pricing":{"input":0.18,"output":0.72,"cache_read":0.018,"cache_write":0.15},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.7,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.75,"context_length":262144,"max_completion_tokens":235929,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":0,"pricing":{"input":0.0875,"output":0.35,"cache_read":0.0175,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-21","knowledge_cutoff":null,"description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1070,"win_rate":49,"rank":109}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":90,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":97.91666666666666,"pricing":{"input":0.09,"output":0.55,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-07-21","knowledge_cutoff":null,"description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1070,"win_rate":49,"rank":109}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.14,"output":0.7999999999999999,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-21","knowledge_cutoff":null,"description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1070,"win_rate":49,"rank":109}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.86111111111111,"pricing":{"input":0.15,"output":0.75,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-21","knowledge_cutoff":null,"description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1070,"win_rate":49,"rank":109}}},{"id":"moonshotai/kimi-k2","name":"MoonshotAI: Kimi K2 0711","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":98304,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.5700000000000001,"output":2.3,"cache_read":null,"cache_write":null},"org":"moonshot","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.7,"coding_index":21,"agentic_index":null,"design_arena_best":{"category":"website","elo":1111,"win_rate":48.8,"rank":108}}},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","name":"Venice: Uncensored","provider":"venice","provider_display":"Venice","quantization":"fp16","discount":0,"context_length":128000,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":0.8999999999999999,"cache_read":null,"cache_write":null},"org":"cognitivecomputations","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"tencent/hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.14,"output":0.5700000000000001,"cache_read":null,"cache_write":null},"org":"tencent","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"tencent/Hunyuan-A13B-Instruct","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-06-30","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"morph/morph-v3-large","name":"Morph: Morph V3 Large","provider":"morph","provider_display":"Morph","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","stop","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.8999999999999999,"output":1.9,"cache_read":null,"cache_write":null},"org":"morph","zdr":true,"modelsdev":{"base_url":"https://api.morphllm.com/v1","model_id":"morph-v3-large","doc_url":"https://docs.morphllm.com/api-reference/introduction","confidence":"high","source":"models.dev","release_date":"2025-07-07","knowledge_cutoff":null,"description":"Flagship model for demanding analysis, coding, and production agent workflows","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"morph/morph-v3-fast","name":"Morph: Morph V3 Fast","provider":"morph","provider_display":"Morph","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","stop","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7999999999999999,"output":1.2,"cache_read":null,"cache_write":null},"org":"morph","zdr":true,"modelsdev":{"base_url":"https://api.morphllm.com/v1","model_id":"morph-v3-fast","doc_url":"https://docs.morphllm.com/api-reference/introduction","confidence":"high","source":"models.dev","release_date":"2025-07-07","knowledge_cutoff":null,"description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","structured_outputs","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.93002099370189,"pricing":{"input":0.075,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":929,"win_rate":43.3,"rank":126}}},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09,"output":0.3,"cache_read":0.049999999999999996,"cache_write":null},"org":"mistral","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":929,"win_rate":43.3,"rank":126}}},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.71929824561403,"pricing":{"input":0.09375,"output":0.25,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":929,"win_rate":43.3,"rank":126}}},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":26214,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.01,"cache_write":null},"org":"mistral","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":929,"win_rate":43.3,"rank":126}}},{"id":"minimax/minimax-m1","name":"MiniMax: MiniMax M1","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":40000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.39999999999999997,"output":2.2,"cache_read":null,"cache_write":null},"org":"minimax","subscription":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1363.8032373271456,"arena_text_rank":202,"arena_text_rating_lower":1359.5108017970663,"arena_text_rating_upper":1368.095672857225,"arena_text_vote_count":34303,"arena_text_date":"2026-10-15","arena_creative_writing":1318.9500091245786,"arena_creative_writing_rank":213,"arena_creative_writing_rating_lower":1309.8447257310415,"arena_creative_writing_rating_upper":1328.0552925181155,"arena_creative_writing_vote_count":4502,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax/minimax-m1","name":"MiniMax: MiniMax M1","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":1000000,"max_completion_tokens":40000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.55,"output":2.2,"cache_read":null,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"minimaxai/minimax-m1-80k","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":null,"description":"Open hybrid-attention MoE reasoning model with a million-token context and an 80K thinking budget","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1363.8032373271456,"arena_text_rank":202,"arena_text_rating_lower":1359.5108017970663,"arena_text_rating_upper":1368.095672857225,"arena_text_vote_count":34303,"arena_text_date":"2026-10-15","arena_creative_writing":1318.9500091245786,"arena_creative_writing_rank":213,"arena_creative_writing_rating_lower":1309.8447257310415,"arena_creative_writing_rating_upper":1328.0552925181155,"arena_creative_writing_vote_count":4502,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-2.5-flash:flex","name":"Google: Gemini 2.5 Flash (flex)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.92987377279103,"pricing":{"input":0.15,"output":1.25,"cache_read":0.015,"cache_write":0.0416666666666667},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1134,"win_rate":49.1,"rank":90},"arena_text":1409.2369734409983,"arena_text_rank":151,"arena_text_rating_lower":1406.7997377325987,"arena_text_rating_upper":1411.6742091493982,"arena_text_vote_count":125521,"arena_text_date":"2026-10-15","arena_creative_writing":1393.8601283158314,"arena_creative_writing_rank":118,"arena_creative_writing_rating_lower":1388.8719634210272,"arena_creative_writing_rating_upper":1398.8482932106353,"arena_creative_writing_vote_count":17664,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.0833333333333333},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1134,"win_rate":49.1,"rank":90},"arena_text":1409.2369734409983,"arena_text_rank":151,"arena_text_rating_lower":1406.7997377325987,"arena_text_rating_upper":1411.6742091493982,"arena_text_vote_count":125521,"arena_text_date":"2026-10-15","arena_creative_writing":1393.8601283158314,"arena_creative_writing_rank":118,"arena_creative_writing_rating_lower":1388.8719634210272,"arena_creative_writing_rating_upper":1398.8482932106353,"arena_creative_writing_vote_count":17664,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-2.5-flash:priority","name":"Google: Gemini 2.5 Flash (priority)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":93.51969504447268,"pricing":{"input":0.54,"output":4.5,"cache_read":0.054,"cache_write":0.15},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1134,"win_rate":49.1,"rank":90},"arena_text":1409.2369734409983,"arena_text_rank":151,"arena_text_rating_lower":1406.7997377325987,"arena_text_rating_upper":1411.6742091493982,"arena_text_vote_count":125521,"arena_text_date":"2026-10-15","arena_creative_writing":1393.8601283158314,"arena_creative_writing_rank":118,"arena_creative_writing_rating_lower":1388.8719634210272,"arena_creative_writing_rating_upper":1398.8482932106353,"arena_creative_writing_vote_count":17664,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-2.5-pro:flex","name":"Google: Gemini 2.5 Pro (flex)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":98.46625766871165,"pricing":{"input":0.625,"output":5,"cache_read":0.0625,"cache_write":0.1875},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-pro","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Google's proven reasoning model for coding, math, and multimodal analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16.1,"coding_index":33.3,"agentic_index":1.6,"design_arena_best":{"category":"dataviz","elo":1222,"win_rate":68.2,"rank":51},"arena_text":1445.413742345976,"arena_text_rank":87,"arena_text_rating_lower":1442.9529937841278,"arena_text_rating_upper":1447.8744909078243,"arena_text_vote_count":125366,"arena_text_date":"2026-10-15","arena_creative_writing":1443.1136532706141,"arena_creative_writing_rank":54,"arena_creative_writing_rating_lower":1437.9911660829816,"arena_creative_writing_rating_upper":1448.2361404582468,"arena_creative_writing_vote_count":17694,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":0.375},"org":"google","zdr":true,"context_price_tiers":[{"above_tokens":200000,"input":2.5,"output":15,"cache_read":0.25,"cache_write":null}],"modelsdev":{"base_url":null,"model_id":"gemini-2.5-pro","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Google's proven reasoning model for coding, math, and multimodal analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16.1,"coding_index":33.3,"agentic_index":1.6,"design_arena_best":{"category":"dataviz","elo":1222,"win_rate":68.2,"rank":51},"arena_text":1445.413742345976,"arena_text_rank":87,"arena_text_rating_lower":1442.9529937841278,"arena_text_rating_upper":1447.8744909078243,"arena_text_vote_count":125366,"arena_text_date":"2026-10-15","arena_creative_writing":1443.1136532706141,"arena_creative_writing_rank":54,"arena_creative_writing_rating_lower":1437.9911660829816,"arena_creative_writing_rating_upper":1448.2361404582468,"arena_creative_writing_vote_count":17694,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-2.5-pro:priority","name":"Google: Gemini 2.5 Pro (priority)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.25,"output":18,"cache_read":0.22499999999999998,"cache_write":0.675},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-pro","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Google's proven reasoning model for coding, math, and multimodal analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":16.1,"coding_index":33.3,"agentic_index":1.6,"design_arena_best":{"category":"dataviz","elo":1222,"win_rate":68.2,"rank":51},"arena_text":1445.413742345976,"arena_text_rank":87,"arena_text_rating_lower":1442.9529937841278,"arena_text_rating_upper":1447.8744909078243,"arena_text_vote_count":125366,"arena_text_date":"2026-10-15","arena_creative_writing":1443.1136532706141,"arena_creative_writing_rank":54,"arena_creative_writing_rating_lower":1437.9911660829816,"arena_creative_writing_rating_upper":1448.2361404582468,"arena_creative_writing_vote_count":17694,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/o3-pro","name":"OpenAI: o3 Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":20,"output":80,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"o3-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-06-10","knowledge_cutoff":"2024-05","description":"High-effort o3 tier for difficult technical reasoning and careful answers","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":21.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"google/gemini-2.5-pro-preview:flex","name":"Google: Gemini 2.5 Pro Preview 06-05 (flex)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":98.46625766871165,"pricing":{"input":0.625,"output":5,"cache_read":0.0625,"cache_write":0.1875},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-pro","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Google's proven reasoning model for coding, math, and multimodal analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1445.413742345976,"arena_text_rank":87,"arena_text_rating_lower":1442.9529937841278,"arena_text_rating_upper":1447.8744909078243,"arena_text_vote_count":125366,"arena_text_date":"2026-10-15","arena_creative_writing":1443.1136532706141,"arena_creative_writing_rank":54,"arena_creative_writing_rating_lower":1437.9911660829816,"arena_creative_writing_rating_upper":1448.2361404582468,"arena_creative_writing_vote_count":17694,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemini-2.5-pro-preview:priority","name":"Google: Gemini 2.5 Pro Preview 06-05 (priority)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","seed","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.25,"output":18,"cache_read":0.22499999999999998,"cache_write":0.675},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-pro","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Google's proven reasoning model for coding, math, and multimodal analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1445.413742345976,"arena_text_rank":87,"arena_text_rating_lower":1442.9529937841278,"arena_text_rating_upper":1447.8744909078243,"arena_text_vote_count":125366,"arena_text_date":"2026-10-15","arena_creative_writing":1443.1136532706141,"arena_creative_writing_rank":54,"arena_creative_writing_rating_lower":1437.9911660829816,"arena_creative_writing_rating_upper":1448.2361404582468,"arena_creative_writing_vote_count":17694,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.7208653175157,"pricing":{"input":0.5,"output":2.1799999999999997,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-05-28","knowledge_cutoff":"2024-07","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1182,"win_rate":60.9,"rank":65},"arena_text":1421.4290222328934,"arena_text_rank":130,"arena_text_rating_lower":1415.7507882696264,"arena_text_rating_upper":1427.1072561961605,"arena_text_vote_count":18167,"arena_text_date":"2026-10-15","arena_creative_writing":1388.8970764882217,"arena_creative_writing_rank":132,"arena_creative_writing_rating_lower":1376.3501553215542,"arena_creative_writing_rating_upper":1401.4439976548892,"arena_creative_writing_vote_count":2408,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":32000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","response_format","structured_outputs","logprobs","top_logprobs","max_tokens","temperature","top_p","stop","presence_penalty"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.68798751950078,"pricing":{"input":0.5710000000000001,"output":2.2859999999999996,"cache_read":null,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-05-28","knowledge_cutoff":"2024-07","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence","reasoning_options":[],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"mit","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1182,"win_rate":60.9,"rank":65},"arena_text":1421.4290222328934,"arena_text_rank":130,"arena_text_rating_lower":1415.7507882696264,"arena_text_rating_upper":1427.1072561961605,"arena_text_vote_count":18167,"arena_text_date":"2026-10-15","arena_creative_writing":1388.8970764882217,"arena_creative_writing_rank":132,"arena_creative_writing_rating_lower":1376.3501553215542,"arena_creative_writing_rating_upper":1401.4439976548892,"arena_creative_writing_vote_count":2408,"arena_creative_writing_date":"2026-10-15"}},{"id":"mistralai/mistral-medium-3","name":"Mistral: Mistral Medium 3","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":104857,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.86363636363636,"pricing":{"input":0.39999999999999997,"output":2,"cache_read":0.04,"cache_write":null},"org":"mistral","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1081,"win_rate":54.7,"rank":94}}},{"id":"meta-llama/llama-guard-4-12b:flex","name":"Meta: Llama Guard 4 12B (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.144,"output":0.144,"cache_read":null,"cache_write":null},"org":"meta","modelsdev":{"base_url":null,"model_id":"meta-llama/Llama-Guard-4-12B","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-04-29","knowledge_cutoff":null,"description":"Multimodal Llama 4-based safety classifier for moderating prompts and responses","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Llama 4 Community License","context_price_tiers":null,"lifecycle_status":null},{"id":"meta-llama/llama-guard-4-12b:priority","name":"Meta: Llama Guard 4 12B (priority)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":97.96491228070175,"pricing":{"input":0.27,"output":0.27,"cache_read":null,"cache_write":null},"org":"meta","modelsdev":{"base_url":null,"model_id":"meta-llama/Llama-Guard-4-12B","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-04-29","knowledge_cutoff":null,"description":"Multimodal Llama 4-based safety classifier for moderating prompts and responses","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Llama 4 Community License","context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen3-14b","name":"Qwen: Qwen3 14B","provider":"nextbit","provider_display":"NextBit","quantization":"int4","discount":0,"context_length":40960,"max_completion_tokens":36864,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","seed","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.22,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":13.8,"agentic_index":0.9,"design_arena_best":null}},{"id":"qwen/qwen3-32b","name":"Qwen: Qwen3 32B","provider":"tenstorrent","provider_display":"Tenstorrent","quantization":"fp8","discount":0,"context_length":20000,"max_completion_tokens":16400,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","temperature","repetition_penalty","top_p","stop","top_k","seed","min_p","max_tokens","top_a","frequency_penalty","logit_bias","presence_penalty","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.14,"output":0.39999999999999997,"cache_read":0.09,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":15.3,"agentic_index":0.9,"design_arena_best":null,"arena_text":1346.8054887198539,"arena_text_rank":223,"arena_text_rating_lower":1337.3482173985908,"arena_text_rating_upper":1356.2627600411167,"arena_text_vote_count":3926,"arena_text_date":"2026-10-15","arena_creative_writing":1303.7112252714267,"arena_creative_writing_rank":233,"arena_creative_writing_rating_lower":1281.09210485787,"arena_creative_writing_rating_upper":1326.330345684983,"arena_creative_writing_vote_count":616,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen3-32b","name":"Qwen: Qwen3 32B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":92.59681093394077,"pricing":{"input":0.14,"output":0.5700000000000001,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.siliconflow.com/v1","model_id":"Qwen/Qwen3-32B","doc_url":"https://cloud.siliconflow.com/models","confidence":"high","source":"models.dev","release_date":"2025-04-28","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"override","license":"apache-2.0","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":15.3,"agentic_index":0.9,"design_arena_best":null,"arena_text":1346.8054887198539,"arena_text_rank":223,"arena_text_rating_lower":1337.3482173985908,"arena_text_rating_upper":1356.2627600411167,"arena_text_vote_count":3926,"arena_text_date":"2026-10-15","arena_creative_writing":1303.7112252714267,"arena_creative_writing_rank":233,"arena_creative_writing_rating_lower":1281.09210485787,"arena_creative_writing_rating_upper":1326.330345684983,"arena_creative_writing_vote_count":616,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/o3","name":"OpenAI: o3","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":100,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":8,"cache_read":0.5,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"o3","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-04-16","knowledge_cutoff":"2024-05","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1200,"win_rate":48.1,"rank":62},"arena_text":1431.6911628578932,"arena_text_rank":112,"arena_text_rating_lower":1428.060676562721,"arena_text_rating_upper":1435.3216491530652,"arena_text_vote_count":58908,"arena_text_date":"2026-10-15","arena_creative_writing":1382.9547314096549,"arena_creative_writing_rank":139,"arena_creative_writing_rating_lower":1375.6482599617518,"arena_creative_writing_rating_upper":1390.2612028575577,"arena_creative_writing_vote_count":7636,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/o3:batch","name":"OpenAI: o3 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1,"output":4,"cache_read":0.25,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"o3","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-04-16","knowledge_cutoff":"2024-05","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":20.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1200,"win_rate":48.1,"rank":62},"arena_text":1431.6911628578932,"arena_text_rank":112,"arena_text_rating_lower":1428.060676562721,"arena_text_rating_upper":1435.3216491530652,"arena_text_vote_count":58908,"arena_text_date":"2026-10-15","arena_creative_writing":1382.9547314096549,"arena_creative_writing_rank":139,"arena_creative_writing_rating_lower":1375.6482599617518,"arena_creative_writing_rating_upper":1390.2612028575577,"arena_creative_writing_vote_count":7636,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/o4-mini:batch","name":"OpenAI: o4 Mini (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","response_format","seed","max_tokens","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.55,"output":2.2,"cache_read":0.1375,"cache_write":null},"org":"openai","lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"o4-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-04-16","knowledge_cutoff":"2024-05","description":"Fast o-series model for compact reasoning, coding, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":16.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1003,"win_rate":50,"rank":123},"arena_text":1391.0547755412438,"arena_text_rank":174,"arena_text_rating_lower":1387.0639782002297,"arena_text_rating_upper":1395.0455728822576,"arena_text_vote_count":44855,"arena_text_date":"2026-10-15","arena_creative_writing":1337.1870039838427,"arena_creative_writing_rank":194,"arena_creative_writing_rating_lower":1328.9771343820935,"arena_creative_writing_rating_upper":1345.396873585592,"arena_creative_writing_vote_count":5786,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-4.1","name":"OpenAI: GPT-4.1","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":942818,"uptime_30m":100,"supported_parameters":["temperature","top_p","max_completion_tokens","tools","tool_choice","structured_outputs","response_format","seed"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":8,"cache_read":0.5,"cache_write":null},"org":"openai","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"gpt-4.1","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":12.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1104,"win_rate":59.5,"rank":98},"arena_text":1414.5863221306088,"arena_text_rank":142,"arena_text_rating_lower":1410.8727571505342,"arena_text_rating_upper":1418.2998871106836,"arena_text_vote_count":50312,"arena_text_date":"2026-10-15","arena_creative_writing":1402.826832681003,"arena_creative_writing_rank":105,"arena_creative_writing_rating_lower":1395.1462835847042,"arena_creative_writing_rating_upper":1410.5073817773018,"arena_creative_writing_vote_count":6650,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-4.1","name":"OpenAI: GPT-4.1","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":8,"cache_read":0.5,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4.1","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1104,"win_rate":59.5,"rank":98},"arena_text":1414.5863221306088,"arena_text_rank":142,"arena_text_rating_lower":1410.8727571505342,"arena_text_rating_upper":1418.2998871106836,"arena_text_vote_count":50312,"arena_text_date":"2026-10-15","arena_creative_writing":1402.826832681003,"arena_creative_writing_rank":105,"arena_creative_writing_rating_lower":1395.1462835847042,"arena_creative_writing_rating_upper":1410.5073817773018,"arena_creative_writing_vote_count":6650,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-4.1:batch","name":"OpenAI: GPT-4.1 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":32768,"uptime_30m":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1,"output":4,"cache_read":0.25,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4.1","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":12.7,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1104,"win_rate":59.5,"rank":98},"arena_text":1414.5863221306088,"arena_text_rank":142,"arena_text_rating_lower":1410.8727571505342,"arena_text_rating_upper":1418.2998871106836,"arena_text_vote_count":50312,"arena_text_date":"2026-10-15","arena_creative_writing":1402.826832681003,"arena_creative_writing_rank":105,"arena_creative_writing_rating_lower":1395.1462835847042,"arena_creative_writing_rating_upper":1410.5073817773018,"arena_creative_writing_vote_count":6650,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":942818,"uptime_30m":100,"supported_parameters":["temperature","top_p","max_completion_tokens","tools","tool_choice","structured_outputs","response_format","seed"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.39999999999999997,"output":1.5999999999999999,"cache_read":0.09999999999999999,"cache_write":null},"org":"openai","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"gpt-4.1-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":10.2,"coding_index":20.2,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1069,"win_rate":58.5,"rank":109},"arena_text":1382.848314009792,"arena_text_rank":187,"arena_text_rating_lower":1378.5149148398377,"arena_text_rating_upper":1387.1817131797459,"arena_text_vote_count":38709,"arena_text_date":"2026-10-15","arena_creative_writing":1348.79015179905,"arena_creative_writing_rank":180,"arena_creative_writing_rating_lower":1339.9876221221577,"arena_creative_writing_rating_upper":1357.5926814759423,"arena_creative_writing_vote_count":5082,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.39999999999999997,"output":1.5999999999999999,"cache_read":0.09999999999999999,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4.1-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":10.2,"coding_index":20.2,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1069,"win_rate":58.5,"rank":109},"arena_text":1382.848314009792,"arena_text_rank":187,"arena_text_rating_lower":1378.5149148398377,"arena_text_rating_upper":1387.1817131797459,"arena_text_vote_count":38709,"arena_text_date":"2026-10-15","arena_creative_writing":1348.79015179905,"arena_creative_writing_rank":180,"arena_creative_writing_rating_lower":1339.9876221221577,"arena_creative_writing_rating_upper":1357.5926814759423,"arena_creative_writing_vote_count":5082,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-4.1-mini:batch","name":"OpenAI: GPT-4.1 Mini (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":32768,"uptime_30m":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.19999999999999998,"output":0.7999999999999999,"cache_read":0.049999999999999996,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4.1-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":10.2,"coding_index":20.2,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1069,"win_rate":58.5,"rank":109},"arena_text":1382.848314009792,"arena_text_rank":187,"arena_text_rating_lower":1378.5149148398377,"arena_text_rating_upper":1387.1817131797459,"arena_text_vote_count":38709,"arena_text_date":"2026-10-15","arena_creative_writing":1348.79015179905,"arena_creative_writing_rank":180,"arena_creative_writing_rating_lower":1339.9876221221577,"arena_creative_writing_rating_upper":1357.5926814759423,"arena_creative_writing_vote_count":5082,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":942818,"uptime_30m":100,"supported_parameters":["temperature","top_p","max_completion_tokens","tool_choice","tools","structured_outputs","response_format","seed"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"gpt-4.1-nano","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":7.8,"coding_index":11.1,"agentic_index":null,"design_arena_best":{"category":"website","elo":971,"win_rate":48.1,"rank":136},"arena_text":1322.2743527841192,"arena_text_rank":258,"arena_text_rating_lower":1314.544138136766,"arena_text_rating_upper":1330.0045674314724,"arena_text_vote_count":6103,"arena_text_date":"2026-10-15","arena_creative_writing":1306.9705540174928,"arena_creative_writing_rank":227,"arena_creative_writing_rating_lower":1288.5270626980987,"arena_creative_writing_rating_upper":1325.4140453368866,"arena_creative_writing_vote_count":1005,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-4.1-nano:batch","name":"OpenAI: GPT-4.1 Nano (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":32768,"uptime_30m":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","temperature","top_p"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.049999999999999996,"output":0.19999999999999998,"cache_read":0.012499999999999999,"cache_write":null},"org":"openai","lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"gpt-4.1-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":7.8,"coding_index":11.1,"agentic_index":null,"design_arena_best":{"category":"website","elo":971,"win_rate":48.1,"rank":136},"arena_text":1322.2743527841192,"arena_text_rank":258,"arena_text_rating_lower":1314.544138136766,"arena_text_rating_upper":1330.0045674314724,"arena_text_vote_count":6103,"arena_text_date":"2026-10-15","arena_creative_writing":1306.9705540174928,"arena_creative_writing_rank":227,"arena_creative_writing_rating_lower":1288.5270626980987,"arena_creative_writing_rating_upper":1325.4140453368866,"arena_creative_writing_vote_count":1005,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["temperature","top_p","max_tokens","response_format","structured_outputs","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.1875,"output":0.6525,"cache_read":0.049999999999999996,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"llama-4-maverick","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for strong reasoning and fast responses","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.3,"coding_index":16.3,"agentic_index":0.6,"design_arena_best":{"category":"3d","elo":898,"win_rate":40.2,"rank":123}}},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":524288,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.35,"output":1,"cache_read":0.16999999999999998,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for strong reasoning and fast responses","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.3,"coding_index":16.3,"agentic_index":0.6,"design_arena_best":{"category":"3d","elo":898,"win_rate":40.2,"rank":123}}},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":524288,"max_completion_tokens":8192,"uptime_30m":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","frequency_penalty","presence_penalty","stop","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.35,"output":1.15,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for strong reasoning and fast responses","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":9.3,"coding_index":16.3,"agentic_index":0.6,"design_arena_best":{"category":"3d","elo":898,"win_rate":40.2,"rank":123}}},{"id":"meta-llama/llama-4-scout:flex","name":"Meta: Llama 4 Scout (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":327680,"max_completion_tokens":294912,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":4.444444444444445,"pricing":{"input":0.08,"output":0.24,"cache_read":null,"cache_write":null},"org":"meta","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.5,"coding_index":8.2,"agentic_index":0.5,"design_arena_best":{"category":"dataviz","elo":896,"win_rate":39.3,"rank":129}}},{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":327680,"max_completion_tokens":16384,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.48453608247422,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":null,"model_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for long-context analysis and efficient agents","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.5,"coding_index":8.2,"agentic_index":0.5,"design_arena_best":{"category":"dataviz","elo":896,"win_rate":39.3,"rank":129}}},{"id":"meta-llama/llama-4-scout:priority","name":"Meta: Llama 4 Scout (priority)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":327680,"max_completion_tokens":294912,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":62.5,"pricing":{"input":0.15,"output":0.44999999999999996,"cache_read":null,"cache_write":null},"org":"meta","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.5,"coding_index":8.2,"agentic_index":0.5,"design_arena_best":{"category":"dataviz","elo":896,"win_rate":39.3,"rank":129}}},{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1310720,"max_completion_tokens":8192,"uptime_30m":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","frequency_penalty","presence_penalty","stop","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.25,"output":0.7,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.5,"coding_index":8.2,"agentic_index":0.5,"design_arena_best":{"category":"dataviz","elo":896,"win_rate":39.3,"rank":129}}},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":100,"supported_parameters":["structured_outputs","response_format","temperature","top_p","top_k","frequency_penalty","tools","tool_choice","max_tokens"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.25,"output":1,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":21.2,"agentic_index":0.8,"design_arena_best":null}},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":115200,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","seed","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.58333333333333,"pricing":{"input":0.29,"output":1.1400000000000001,"cache_read":0.11,"cache_write":null},"org":"deepseek","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":21.2,"agentic_index":0.8,"design_arena_best":null}},{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":102400,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","logprobs","top_logprobs","tools","tool_choice","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.351,"output":0.5549999999999999,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/mistralai/mistral-small-3.1-24b-instruct","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2025-03-17","knowledge_cutoff":"2024-06","description":"Efficient Mistral model for fast chat, extraction, and production assistants","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"google/gemma-3-4b-it","name":"Google: Gemma 3 4B","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.04,"output":0.049999999999999996,"cache_read":0.02,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-03-12","knowledge_cutoff":"2024-08","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":2.7,"agentic_index":null,"design_arena_best":null,"arena_text":1303.262118441158,"arena_text_rank":284,"arena_text_rating_lower":1293.945083293274,"arena_text_rating_upper":1312.5791535890423,"arena_text_vote_count":4171,"arena_text_date":"2026-10-15","arena_creative_writing":1274.590709714658,"arena_creative_writing_rank":272,"arena_creative_writing_rating_lower":1252.2953144263392,"arena_creative_writing_rating_upper":1296.8861050029766,"arena_creative_writing_vote_count":666,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-3-12b-it:flex","name":"Google: Gemma 3 12B (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":67.3076923076923,"pricing":{"input":0.04,"output":0.12,"cache_read":null,"cache_write":null},"org":"google","modelsdev":{"base_url":null,"model_id":"google/gemma-3-12b-it","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-03-12","knowledge_cutoff":"2024-08","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":5.8,"agentic_index":0.1,"design_arena_best":null,"arena_text":1341.7699741013544,"arena_text_rank":233,"arena_text_rating_lower":1332.2584502580542,"arena_text_rating_upper":1351.2814979446548,"arena_text_vote_count":3829,"arena_text_date":"2026-10-15","arena_creative_writing":1332.6341732820492,"arena_creative_writing_rank":200,"arena_creative_writing_rating_lower":1309.3689418803422,"arena_creative_writing_rating_upper":1355.8994046837565,"arena_creative_writing_vote_count":600,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-3-12b-it","name":"Google: Gemma 3 12B","provider":"nextbit","provider_display":"NextBit","quantization":"int4","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.075,"output":0.15,"cache_read":0.049999999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-03-12","knowledge_cutoff":"2024-08","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":5.8,"agentic_index":0.1,"design_arena_best":null,"arena_text":1341.7699741013544,"arena_text_rank":233,"arena_text_rating_lower":1332.2584502580542,"arena_text_rating_upper":1351.2814979446548,"arena_text_vote_count":3829,"arena_text_date":"2026-10-15","arena_creative_writing":1332.6341732820492,"arena_creative_writing_rank":200,"arena_creative_writing_rating_lower":1309.3689418803422,"arena_creative_writing_rating_upper":1355.8994046837565,"arena_creative_writing_vote_count":600,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-3-12b-it:priority","name":"Google: Gemma 3 12B (priority)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":95.71026722925457,"pricing":{"input":0.075,"output":0.22499999999999998,"cache_read":null,"cache_write":null},"org":"google","modelsdev":{"base_url":null,"model_id":"google/gemma-3-12b-it","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2025-03-12","knowledge_cutoff":"2024-08","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":5.8,"agentic_index":0.1,"design_arena_best":null,"arena_text":1341.7699741013544,"arena_text_rank":233,"arena_text_rating_lower":1332.2584502580542,"arena_text_rating_upper":1351.2814979446548,"arena_text_vote_count":3829,"arena_text_date":"2026-10-15","arena_creative_writing":1332.6341732820492,"arena_creative_writing_rank":200,"arena_creative_writing_rating_lower":1309.3689418803422,"arena_creative_writing_rating_upper":1355.8994046837565,"arena_creative_writing_vote_count":600,"arena_creative_writing_date":"2026-10-15"}},{"id":"cohere/command-a","name":"Cohere: Command A","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.5,"output":10,"cache_read":null,"cache_write":null},"org":"cohere","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":7,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"rekaai/reka-flash-3","name":"Reka Flash 3","provider":"reka","provider_display":"Reka","quantization":"unknown","discount":0,"context_length":65536,"max_completion_tokens":58982,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","structured_outputs","logprobs","top_logprobs","temperature","top_p","top_k","max_tokens","stop","seed","frequency_penalty","presence_penalty"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.09999999999999999,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"rekaai","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","provider":"nextbit","provider_display":"NextBit","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":96.66666666666667,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":94.09722222222221,"pricing":{"input":0.08,"output":0.35,"cache_read":0.04,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-03-12","knowledge_cutoff":"2024-08","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":10.1,"agentic_index":0.1,"design_arena_best":null,"arena_text":1365.4528659816333,"arena_text_rank":200,"arena_text_rating_lower":1361.7493134028653,"arena_text_rating_upper":1369.1564185604013,"arena_text_vote_count":46666,"arena_text_date":"2026-10-15","arena_creative_writing":1348.3838436543454,"arena_creative_writing_rank":182,"arena_creative_writing_rating_lower":1340.6538455393713,"arena_creative_writing_rating_upper":1356.1138417693194,"arena_creative_writing_vote_count":6308,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":96.66666666666667,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":98.52838121934127,"pricing":{"input":0.08,"output":0.44999999999999996,"cache_read":0.04,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-03-12","knowledge_cutoff":"2024-08","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":10.1,"agentic_index":0.1,"design_arena_best":null,"arena_text":1365.4528659816333,"arena_text_rank":200,"arena_text_rating_lower":1361.7493134028653,"arena_text_rating_upper":1369.1564185604013,"arena_text_vote_count":46666,"arena_text_date":"2026-10-15","arena_creative_writing":1348.3838436543454,"arena_creative_writing_rank":182,"arena_creative_writing_rating_lower":1340.6538455393713,"arena_creative_writing_rating_upper":1356.1138417693194,"arena_creative_writing_vote_count":6308,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":110000,"max_completion_tokens":99000,"uptime_30m":89.65517241379311,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","logit_bias","structured_outputs","response_format","repetition_penalty"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":100000,"uptime_1d":89.21933085501858,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.04,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"google/gemma-3-27b-it","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2025-03-12","knowledge_cutoff":"2024-08","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":10.1,"agentic_index":0.1,"design_arena_best":null,"arena_text":1365.4528659816333,"arena_text_rank":200,"arena_text_rating_lower":1361.7493134028653,"arena_text_rating_upper":1369.1564185604013,"arena_text_vote_count":46666,"arena_text_date":"2026-10-15","arena_creative_writing":1348.3838436543454,"arena_creative_writing_rank":182,"arena_creative_writing_rating_lower":1340.6538455393713,"arena_creative_writing_rating_upper":1356.1138417693194,"arena_creative_writing_vote_count":6308,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":98304,"max_completion_tokens":16384,"uptime_30m":90,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":97.00427960057061,"pricing":{"input":0.119,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"google/gemma-3-27b-it","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-03-12","knowledge_cutoff":"2024-08","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":10.1,"agentic_index":0.1,"design_arena_best":null,"arena_text":1365.4528659816333,"arena_text_rank":200,"arena_text_rating_lower":1361.7493134028653,"arena_text_rating_upper":1369.1564185604013,"arena_text_vote_count":46666,"arena_text_date":"2026-10-15","arena_creative_writing":1348.3838436543454,"arena_creative_writing_rank":182,"arena_creative_writing_rating_lower":1340.6538455393713,"arena_creative_writing_rating_upper":1356.1138417693194,"arena_creative_writing_vote_count":6308,"arena_creative_writing_date":"2026-10-15"}},{"id":"thedrummer/skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":32768,"max_completion_tokens":29491,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.42196531791907,"pricing":{"input":0.55,"output":0.7999999999999999,"cache_read":0.25,"cache_write":null},"org":"thedrummer","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"perplexity/sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","provider":"perplexity","provider_display":"Perplexity","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":115200,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":8,"cache_read":null,"cache_write":null},"org":"perplexity","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"sonar-reasoning-pro","doc_url":"https://docs.perplexity.ai","confidence":"high","source":"models.dev","release_date":"2024-01-01","knowledge_cutoff":"2025-09-01","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":11.8,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"perplexity/sonar-pro","name":"Perplexity: Sonar Pro","provider":"perplexity","provider_display":"Perplexity","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":8000,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":15,"cache_read":null,"cache_write":null},"org":"perplexity","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"sonar-pro","doc_url":"https://docs.perplexity.ai","confidence":"high","source":"models.dev","release_date":"2024-01-01","knowledge_cutoff":"2025-09-01","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":7.6,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"perplexity/sonar-deep-research","name":"Perplexity: Sonar Deep Research","provider":"perplexity","provider_display":"Perplexity","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":115200,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":8,"cache_read":null,"cache_write":null},"org":"perplexity","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"sonar-deep-research","doc_url":"https://docs.perplexity.ai","confidence":"high","source":"models.dev","release_date":"2025-02-01","knowledge_cutoff":"2025-01","description":"Sonar search model for current answers, retrieval, and citation-backed chat","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null},{"id":"mistralai/mistral-saba","name":"Mistral: Saba","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":26214,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":0.6,"cache_read":0.02,"cache_write":null},"org":"mistral","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.5,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","provider":"aionlabs","provider_display":"AionLabs","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":29491,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7999999999999999,"output":1.5999999999999999,"cache_read":null,"cache_write":null},"org":"aion-labs","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":115200,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.92912827781714,"pricing":{"input":0.7999999999999999,"output":1,"cache_read":0.39999999999999997,"cache_write":null},"org":"qwen","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen-plus","name":"Qwen: Qwen-Plus","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","seed","presence_penalty","response_format","tools","tool_choice","structured_outputs","logprobs","top_logprobs","top_k","frequency_penalty","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":995904,"uptime_1d":95.51724137931035,"pricing":{"input":0.26,"output":0.78,"cache_read":0.052000000000000005,"cache_write":0.325},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen-plus","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2024-01-25","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/o3-mini:batch","name":"OpenAI: o3 Mini (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"supported_parameters":["reasoning","include_reasoning","seed","max_tokens","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.55,"output":2.2,"cache_read":0.275,"cache_write":null},"org":"openai","lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"o3-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2024-12-20","knowledge_cutoff":"2024-05","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":12.5,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1348.0956335428316,"arena_text_rank":220,"arena_text_rating_lower":1344.540776306856,"arena_text_rating_upper":1351.6504907788071,"arena_text_vote_count":56741,"arena_text_date":"2026-10-15","arena_creative_writing":1301.2111409093238,"arena_creative_writing_rank":239,"arena_creative_writing_rating_lower":1294.2160692685036,"arena_creative_writing_rating_upper":1308.2062125501443,"arena_creative_writing_vote_count":8163,"arena_creative_writing_date":"2026-10-15"}},{"id":"perplexity/sonar","name":"Perplexity: Sonar","provider":"perplexity","provider_display":"Perplexity","quantization":"unknown","discount":0,"context_length":127072,"max_completion_tokens":114364,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","frequency_penalty","presence_penalty","web_search_options"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":1,"cache_read":null,"cache_write":null},"org":"perplexity","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"sonar","doc_url":"https://docs.perplexity.ai","confidence":"high","source":"models.dev","release_date":"2024-01-01","knowledge_cutoff":"2025-09-01","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":7.7,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"minimax/minimax-01","name":"MiniMax: MiniMax-01","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":1000192,"max_completion_tokens":900172,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":1.1,"cache_read":null,"cache_write":null},"org":"minimax","subscription":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"microsoft/phi-4:flex","name":"Microsoft: Phi 4 (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":16384,"max_completion_tokens":14745,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.056,"output":0.112,"cache_read":null,"cache_write":null},"org":"microsoft","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1256.3106977286461,"arena_text_rank":320,"arena_text_rating_lower":1251.6997685220442,"arena_text_rating_upper":1260.921626935248,"arena_text_vote_count":24126,"arena_text_date":"2026-10-15","arena_creative_writing":1210.0709700014152,"arena_creative_writing_rank":319,"arena_creative_writing_rating_lower":1200.3295738650274,"arena_creative_writing_rating_upper":1219.8123661378029,"arena_creative_writing_vote_count":4062,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek/deepseek-chat:flex","name":"DeepSeek: DeepSeek V3 (flex)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":163840,"max_completion_tokens":147456,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.256,"output":0.7120000000000001,"cache_read":null,"cache_write":null},"org":"deepseek","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1118,"win_rate":48.5,"rank":105}}},{"id":"deepseek/deepseek-chat","name":"DeepSeek: DeepSeek V3","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0.1,"context_length":128000,"max_completion_tokens":16000,"uptime_30m":100,"supported_parameters":["response_format","structured_outputs","tools","tool_choice","max_tokens","temperature","top_p","stop","presence_penalty"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.2574,"output":1.0287,"cache_read":null,"cache_write":null},"org":"deepseek","open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1118,"win_rate":48.5,"rank":105}}},{"id":"deepseek/deepseek-chat","name":"DeepSeek: DeepSeek V3","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":163840,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","structured_outputs","tools","tool_choice","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.44250871080139,"pricing":{"input":0.32,"output":0.8899999999999999,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1118,"win_rate":48.5,"rank":105}}},{"id":"cohere/command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":4000,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.0375,"output":0.15,"cache_read":null,"cache_write":null},"org":"cohere","modelsdev":{"base_url":null,"model_id":"command-r7b-12-2024","doc_url":"https://docs.cohere.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-12-13","knowledge_cutoff":"2024-06-01","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct (turbo)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.09999999999999999,"output":0.32,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":null,"model_id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","doc_url":"https://deepinfra.com/models","confidence":"medium","source":"models.dev","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Compact Llama instruction model for fast chat and local deployment","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null,"design_arena_best":null,"arena_text":1318.0654473917496,"arena_text_rank":264,"arena_text_rating_lower":1314.561524832038,"arena_text_rating_upper":1321.569369951461,"arena_text_vote_count":54497,"arena_text_date":"2026-10-15","arena_creative_writing":1285.365717788876,"arena_creative_writing_rank":257,"arena_creative_writing_rating_lower":1278.3092286350516,"arena_creative_writing_rating_upper":1292.4222069427008,"arena_creative_writing_vote_count":8046,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":12288,"max_completion_tokens":11059,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.5125348189415,"pricing":{"input":0.135,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"meta-llama/llama-3.3-70b-instruct","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null,"design_arena_best":null,"arena_text":1318.0654473917496,"arena_text_rank":264,"arena_text_rating_lower":1314.561524832038,"arena_text_rating_upper":1321.569369951461,"arena_text_vote_count":54497,"arena_text_date":"2026-10-15","arena_creative_writing":1285.365717788876,"arena_creative_writing_rank":257,"arena_creative_writing_rating_lower":1278.3092286350516,"arena_creative_writing_rating_upper":1292.4222069427008,"arena_creative_writing_vote_count":8046,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"akashml","provider_display":"AkashML","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":128000,"uptime_30m":100,"supported_parameters":["temperature","top_p","top_k","stop","frequency_penalty","presence_penalty","repetition_penalty","seed","max_tokens","structured_outputs","tools","tool_choice","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.19999999999999998,"output":0.52,"cache_read":0.09999999999999999,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null,"design_arena_best":null,"arena_text":1318.0654473917496,"arena_text_rank":264,"arena_text_rating_lower":1314.561524832038,"arena_text_rating_upper":1321.569369951461,"arena_text_vote_count":54497,"arena_text_date":"2026-10-15","arena_creative_writing":1285.365717788876,"arena_creative_writing_rank":257,"arena_creative_writing_rating_lower":1278.3092286350516,"arena_creative_writing_rating_upper":1292.4222069427008,"arena_creative_writing_vote_count":8046,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.22,"output":0.5,"cache_read":0.11,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null,"design_arena_best":null,"arena_text":1318.0654473917496,"arena_text_rank":264,"arena_text_rating_lower":1314.561524832038,"arena_text_rating_upper":1321.569369951461,"arena_text_vote_count":54497,"arena_text_date":"2026-10-15","arena_creative_writing":1285.365717788876,"arena_creative_writing_rank":257,"arena_creative_writing_rating_lower":1278.3092286350516,"arena_creative_writing_rating_upper":1292.4222069427008,"arena_creative_writing_vote_count":8046,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"cloudflare","provider_display":"Cloudflare","quantization":"fp8","discount":0,"context_length":24000,"max_completion_tokens":21600,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.293,"output":2.2529999999999997,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"medium","source":"models.dev","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null,"design_arena_best":null,"arena_text":1318.0654473917496,"arena_text_rank":264,"arena_text_rating_lower":1314.561524832038,"arena_text_rating_upper":1321.569369951461,"arena_text_vote_count":54497,"arena_text_date":"2026-10-15","arena_creative_writing":1285.365717788876,"arena_creative_writing_rank":257,"arena_creative_writing_rating_lower":1278.3092286350516,"arena_creative_writing_rating_upper":1292.4222069427008,"arena_creative_writing_vote_count":8046,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"sambanova","provider_display":"SambaNova","quantization":"unknown","discount":0.25,"context_length":131072,"max_completion_tokens":3072,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":97.33707077785564,"pricing":{"input":0.44999999999999996,"output":0.8999999999999999,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null,"design_arena_best":null,"arena_text":1318.0654473917496,"arena_text_rank":264,"arena_text_rating_lower":1314.561524832038,"arena_text_rating_upper":1321.569369951461,"arena_text_vote_count":54497,"arena_text_date":"2026-10-15","arena_creative_writing":1285.365717788876,"arena_creative_writing_rank":257,"arena_creative_writing_rating_lower":1278.3092286350516,"arena_creative_writing_rating_upper":1292.4222069427008,"arena_creative_writing_vote_count":8046,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.59,"output":0.7899999999999999,"cache_read":0.295,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null,"design_arena_best":null,"arena_text":1318.0654473917496,"arena_text_rank":264,"arena_text_rating_lower":1314.561524832038,"arena_text_rating_upper":1321.569369951461,"arena_text_vote_count":54497,"arena_text_date":"2026-10-15","arena_creative_writing":1285.365717788876,"arena_creative_writing_rank":257,"arena_creative_writing_rating_lower":1278.3092286350516,"arena_creative_writing_rating_upper":1292.4222069427008,"arena_creative_writing_vote_count":8046,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp16","discount":0,"context_length":128000,"max_completion_tokens":115200,"uptime_30m":100,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.71,"output":0.71,"cache_read":0.71,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null,"design_arena_best":null,"arena_text":1318.0654473917496,"arena_text_rank":264,"arena_text_rating_lower":1314.561524832038,"arena_text_rating_upper":1321.569369951461,"arena_text_vote_count":54497,"arena_text_date":"2026-10-15","arena_creative_writing":1285.365717788876,"arena_creative_writing_rank":257,"arena_creative_writing_rating_lower":1278.3092286350516,"arena_creative_writing_rating_upper":1292.4222069427008,"arena_creative_writing_vote_count":8046,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":8192,"uptime_30m":null,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","seed","top_k","frequency_penalty","presence_penalty","stop","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.72,"output":0.72,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.crusoecloud.com/managed-inference/overview","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":11.9,"agentic_index":null,"design_arena_best":null,"arena_text":1318.0654473917496,"arena_text_rank":264,"arena_text_rating_lower":1314.561524832038,"arena_text_rating_upper":1321.569369951461,"arena_text_vote_count":54497,"arena_text_date":"2026-10-15","arena_creative_writing":1285.365717788876,"arena_creative_writing_rank":257,"arena_creative_writing_rating_lower":1278.3092286350516,"arena_creative_writing_rating_upper":1292.4222069427008,"arena_creative_writing_vote_count":8046,"arena_creative_writing_date":"2026-10-15"}},{"id":"amazon/nova-lite-v1","name":"Amazon: Nova Lite 1.0","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":300000,"max_completion_tokens":5120,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.38042131350682,"pricing":{"input":0.06,"output":0.24,"cache_read":0.015,"cache_write":0.06},"org":"amazon","zdr":true,"modelsdev":{"base_url":null,"model_id":"us.amazon.nova-lite-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2024-12-03","knowledge_cutoff":"2024-10","description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"amazon/nova-micro-v1","name":"Amazon: Nova Micro 1.0","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":5120,"uptime_30m":66.66666666666666,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":88.28125,"pricing":{"input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":0.035},"org":"amazon","zdr":true,"modelsdev":{"base_url":null,"model_id":"amazon.nova-micro-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2024-12-03","knowledge_cutoff":"2024-10","description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"amazon/nova-pro-v1","name":"Amazon: Nova Pro 1.0","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":300000,"max_completion_tokens":5120,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop","tools"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7999999999999999,"output":3.1999999999999997,"cache_read":0.2,"cache_write":0.8},"org":"amazon","zdr":true,"modelsdev":{"base_url":null,"model_id":"amazon.nova-pro-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2024-12-03","knowledge_cutoff":"2024-10","description":"Flagship model for demanding analysis, coding, and production agent workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":794,"win_rate":21.4,"rank":147}}},{"id":"openai/gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","frequency_penalty","logit_bias","logprobs","prediction","presence_penalty","stop","temperature","top_logprobs","top_p","web_search_options"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.5,"output":10,"cache_read":1.25,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4o-2024-11-20","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-11-20","knowledge_cutoff":"2023-09","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":8.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":906,"win_rate":42.3,"rank":136},"arena_text":1346.1327118570525,"arena_text_rank":225,"arena_text_rating_lower":1342.6666387157807,"arena_text_rating_upper":1349.5987849983242,"arena_text_vote_count":112881,"arena_text_date":"2026-10-15","arena_creative_writing":1337.5936624648746,"arena_creative_writing_rank":193,"arena_creative_writing_rating_lower":1330.4173187854085,"arena_creative_writing_rating_upper":1344.7700061443406,"arena_creative_writing_vote_count":16599,"arena_creative_writing_date":"2026-10-15"}},{"id":"mistralai/mistral-large-2407","name":"Mistral Large 2407","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":104857,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":2,"output":6,"cache_read":0.19999999999999998,"cache_write":null},"org":"mistral","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.8,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1314.4464446749162,"arena_text_rank":269,"arena_text_rating_lower":1310.512481270608,"arena_text_rating_upper":1318.380408079224,"arena_text_vote_count":45459,"arena_text_date":"2026-10-15","arena_creative_writing":1287.3780934174986,"arena_creative_writing_rank":254,"arena_creative_writing_rating_lower":1278.700817898635,"arena_creative_writing_rating_upper":1296.055368936362,"arena_creative_writing_vote_count":6692,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":29491,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.66,"output":1,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"thedrummer/unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":1024000,"max_completion_tokens":819200,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.39999999999999997,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"thedrummer","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":32768,"max_completion_tokens":4096,"uptime_30m":100,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.5,"output":5,"cache_read":null,"cache_write":null},"org":"anthracite-org","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen/qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":29491,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","min_p","repetition_penalty","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.86111111111111,"pricing":{"input":0.09999999999999999,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"meta-llama/llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":60000,"max_completion_tokens":54000,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.027,"output":0.201,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/meta/llama-3.2-1b-instruct","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2024-09-25","knowledge_cutoff":"2023-12","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Llama 3.2 Community License","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1111.1932734500465,"arena_text_rank":398,"arena_text_rating_lower":1103.3149378770254,"arena_text_rating_upper":1119.0716090230678,"arena_text_vote_count":8045,"arena_text_date":"2026-10-15","arena_creative_writing":1082.4232864230457,"arena_creative_writing_rank":395,"arena_creative_writing_rating_lower":1061.6777881634628,"arena_creative_writing_rating_upper":1103.1687846826285,"arena_creative_writing_vote_count":1091,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.049999999999999996,"output":0.33,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-09-25","knowledge_cutoff":"2023-12","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://developers.cloudflare.com/workers-ai/models/","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Llama 3.2 Community License","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1166.8651083152117,"arena_text_rank":369,"arena_text_rating_lower":1159.1636238540268,"arena_text_rating_upper":1174.5665927763966,"arena_text_vote_count":7936,"arena_text_date":"2026-10-15","arena_creative_writing":1144.5154965194276,"arena_creative_writing_rank":359,"arena_creative_writing_rating_lower":1124.7803795256425,"arena_creative_writing_rating_upper":1164.2506135132128,"arena_creative_writing_vote_count":1070,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":80000,"max_completion_tokens":72000,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.0509,"output":0.335,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/meta/llama-3.2-3b-instruct","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2024-09-25","knowledge_cutoff":"2023-12","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":"Llama 3.2 Community License","context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1166.8651083152117,"arena_text_rank":369,"arena_text_rating_lower":1159.1636238540268,"arena_text_rating_upper":1174.5665927763966,"arena_text_vote_count":7936,"arena_text_date":"2026-10-15","arena_creative_writing":1144.5154965194276,"arena_creative_writing_rank":359,"arena_creative_writing_rating_lower":1124.7803795256425,"arena_creative_writing_rating_upper":1164.2506135132128,"arena_creative_writing_vote_count":1070,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":32768,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":98.34532374100719,"pricing":{"input":0.36,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"cohere/command-r-08-2024","name":"Cohere: Command R (08-2024)","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":4000,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"cohere","modelsdev":{"base_url":null,"model_id":"command-r-08-2024","doc_url":"https://docs.cohere.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-08-30","knowledge_cutoff":"2024-06-01","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1250.526523412432,"arena_text_rank":322,"arena_text_rating_lower":1243.924103751033,"arena_text_rating_upper":1257.128943073831,"arena_text_vote_count":10140,"arena_text_date":"2026-10-15","arena_creative_writing":1208.9967443380435,"arena_creative_writing_rank":320,"arena_creative_writing_rating_lower":1193.3291128687197,"arena_creative_writing_rating_upper":1224.6643758073674,"arena_creative_writing_vote_count":1421,"arena_creative_writing_date":"2026-10-15"}},{"id":"cohere/command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":4000,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","top_k","seed","structured_outputs","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.5,"output":10,"cache_read":null,"cache_write":null},"org":"cohere","modelsdev":{"base_url":null,"model_id":"command-r-plus-08-2024","doc_url":"https://docs.cohere.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-08-30","knowledge_cutoff":"2024-06-01","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1276.3819106946182,"arena_text_rank":306,"arena_text_rating_lower":1269.804145679302,"arena_text_rating_upper":1282.9596757099343,"arena_text_vote_count":9866,"arena_text_date":"2026-10-15","arena_creative_writing":1262.741228184961,"arena_creative_writing_rank":286,"arena_creative_writing_rating_lower":1247.6616299947111,"arena_creative_writing_rating_upper":1277.8208263752108,"arena_creative_writing_vote_count":1474,"arena_creative_writing_date":"2026-10-15"}},{"id":"sao10k/l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.85,"output":0.85,"cache_read":null,"cache_write":null},"org":"sao10k","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"nousresearch/hermes-3-llama-3.1-70b","name":"Nous: Hermes 3 70B Instruct","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.7,"output":0.7,"cache_read":null,"cache_write":null},"org":"nous","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"nousresearch/hermes-3-llama-3.1-405b","name":"Nous: Hermes 3 405B Instruct","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","structured_outputs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":98.67617107942974,"pricing":{"input":1,"output":1,"cache_read":null,"cache_write":null},"org":"nous","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-08-16","knowledge_cutoff":"2023-12-31","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.venice.ai","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"sao10k/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":8192,"max_completion_tokens":7372,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.79152189020152,"pricing":{"input":0.04,"output":0.049999999999999996,"cache_read":null,"cache_write":null},"org":"sao10k","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"sao10k/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris (turbo)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":8192,"max_completion_tokens":7372,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.04,"output":0.049999999999999996,"cache_read":null,"cache_write":null},"org":"sao10k","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["temperature","top_p","max_completion_tokens","tools","tool_choice","stop","frequency_penalty","presence_penalty","web_search_options","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2.5,"output":10,"cache_read":1.25,"cache_write":null},"org":"openai","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"gpt-4o","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2024-05-13","knowledge_cutoff":"2023-09","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":8.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":906,"win_rate":42.3,"rank":136},"arena_text":1346.1327118570525,"arena_text_rank":225,"arena_text_rating_lower":1342.6666387157807,"arena_text_rating_upper":1349.5987849983242,"arena_text_vote_count":112881,"arena_text_date":"2026-10-15","arena_creative_writing":1337.5936624648746,"arena_creative_writing_rank":193,"arena_creative_writing_rating_lower":1330.4173187854085,"arena_creative_writing_rating_upper":1344.7700061443406,"arena_creative_writing_vote_count":16599,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct (turbo)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.22425952045134,"pricing":{"input":0.39999999999999997,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1293.3762260694427,"arena_text_rank":289,"arena_text_rating_lower":1289.6286323610916,"arena_text_rating_upper":1297.1238197777939,"arena_text_vote_count":55240,"arena_text_date":"2026-10-15","arena_creative_writing":1256.9774249950292,"arena_creative_writing_rank":290,"arena_creative_writing_rating_lower":1249.1214535190693,"arena_creative_writing_rating_upper":1264.8333964709889,"arena_creative_writing_vote_count":8250,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","stop"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.72,"output":0.72,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":null,"model_id":"us.meta.llama3-1-70b-instruct-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"medium","source":"models.dev","release_date":"2024-07-23","knowledge_cutoff":"2023-12","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1293.3762260694427,"arena_text_rank":289,"arena_text_rating_lower":1289.6286323610916,"arena_text_rating_upper":1297.1238197777939,"arena_text_vote_count":55240,"arena_text_date":"2026-10-15","arena_creative_writing":1256.9774249950292,"arena_creative_writing_rank":290,"arena_creative_writing_rating_lower":1249.1214535190693,"arena_creative_writing_rating_upper":1264.8333964709889,"arena_creative_writing_vote_count":8250,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.229152067274,"pricing":{"input":0.02,"output":0.04,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-07-23","knowledge_cutoff":"2023-12","description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":5.4,"agentic_index":null,"design_arena_best":null,"arena_text":1211.2299856226907,"arena_text_rank":343,"arena_text_rating_lower":1207.0682111539336,"arena_text_rating_upper":1215.3917600914476,"arena_text_vote_count":49605,"arena_text_date":"2026-10-15","arena_creative_writing":1177.0939803061635,"arena_creative_writing_rank":342,"arena_creative_writing_rating_lower":1168.6099028263632,"arena_creative_writing_rating_upper":1185.5780577859637,"arena_creative_writing_vote_count":7346,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":16384,"max_completion_tokens":14745,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.02,"output":0.049999999999999996,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"meta-llama/llama-3.1-8b-instruct","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2024-07-23","knowledge_cutoff":"2023-12","description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":5.4,"agentic_index":null,"design_arena_best":null,"arena_text":1211.2299856226907,"arena_text_rank":343,"arena_text_rating_lower":1207.0682111539336,"arena_text_rating_upper":1215.3917600914476,"arena_text_vote_count":49605,"arena_text_date":"2026-10-15","arena_creative_writing":1177.0939803061635,"arena_creative_writing_rank":342,"arena_creative_writing_rating_lower":1168.6099028263632,"arena_creative_writing_rating_upper":1185.5780577859637,"arena_creative_writing_vote_count":7346,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.049999999999999996,"output":0.08,"cache_read":0.024999999999999998,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-07-23","knowledge_cutoff":"2023-12","description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":5.4,"agentic_index":null,"design_arena_best":null,"arena_text":1211.2299856226907,"arena_text_rank":343,"arena_text_rating_lower":1207.0682111539336,"arena_text_rating_upper":1215.3917600914476,"arena_text_vote_count":49605,"arena_text_date":"2026-10-15","arena_creative_writing":1177.0939803061635,"arena_creative_writing_rank":342,"arena_creative_writing_rating_lower":1168.6099028263632,"arena_creative_writing_rating_upper":1185.5780577859637,"arena_creative_writing_vote_count":7346,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"cloudflare","provider_display":"Cloudflare","quantization":"fp8","discount":0,"context_length":32000,"max_completion_tokens":28800,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15200000000000002,"output":0.28700000000000003,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":null,"model_id":"@cf/meta/llama-3.1-8b-instruct-fp8","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"medium","source":"models.dev","release_date":"2024-07-23","knowledge_cutoff":"2023-12","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":5.4,"agentic_index":null,"design_arena_best":null,"arena_text":1211.2299856226907,"arena_text_rank":343,"arena_text_rating_lower":1207.0682111539336,"arena_text_rating_upper":1215.3917600914476,"arena_text_vote_count":49605,"arena_text_date":"2026-10-15","arena_creative_writing":1177.0939803061635,"arena_creative_writing_rank":342,"arena_creative_writing_rating_lower":1168.6099028263632,"arena_creative_writing_rating_upper":1185.5780577859637,"arena_creative_writing_vote_count":7346,"arena_creative_writing_date":"2026-10-15"}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"coreweave","provider_display":"CoreWeave","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":117964,"uptime_30m":100,"supported_parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.22,"output":0.22,"cache_read":0.22,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-07-23","knowledge_cutoff":"2023-12","description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.wandb.ai/inference","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":5.4,"agentic_index":null,"design_arena_best":null,"arena_text":1211.2299856226907,"arena_text_rank":343,"arena_text_rating_lower":1207.0682111539336,"arena_text_rating_upper":1215.3917600914476,"arena_text_vote_count":49605,"arena_text_date":"2026-10-15","arena_creative_writing":1177.0939803061635,"arena_creative_writing_rank":342,"arena_creative_writing_rating_lower":1168.6099028263632,"arena_creative_writing_rating_upper":1185.5780577859637,"arena_creative_writing_vote_count":7346,"arena_creative_writing_date":"2026-10-15"}},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","provider":"io-net","provider_display":"Io Net","quantization":"fp16","discount":0.28,"context_length":128000,"max_completion_tokens":102400,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","seed","stop","min_p","top_k","top_p","presence_penalty","frequency_penalty","repetition_penalty","logprobs","top_logprobs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.016560000000000002,"output":0.0216,"cache_read":0.0108,"cache_write":null},"org":"mistral","zdr":true,"modelsdev":{"base_url":"https://api.intelligence.io.solutions/api/v1","model_id":"mistralai/Mistral-Nemo-Instruct-2407","doc_url":"https://io.net/docs/guides/intelligence/io-intelligence","confidence":"medium","source":"models.dev","release_date":"2024-07-18","knowledge_cutoff":"2024-05","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","provider":"dekallm","provider_display":"DekaLLM","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":104857,"uptime_30m":100,"supported_parameters":["frequency_penalty","logit_bias","max_tokens","presence_penalty","seed","stop","temperature","top_p","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.86082115518441,"pricing":{"input":0.018,"output":0.03,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.029,"output":0.03,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":104857,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","response_format","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":99.15314043754411,"pricing":{"input":0.03,"output":0.03,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":104857,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.15,"cache_read":0.015,"cache_write":null},"org":"mistral","zdr":true,"modelsdev":{"base_url":null,"model_id":"open-mistral-nemo","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"medium","source":"models.dev","release_date":"2024-07-01","knowledge_cutoff":"2024-07","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["temperature","top_p","max_completion_tokens","stop","frequency_penalty","presence_penalty","web_search_options","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":99.93055555555556,"pricing":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":null},"org":"openai","zdr":true,"lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"gpt-4o-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2024-07-18","knowledge_cutoff":"2023-09","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":6.7,"coding_index":11.4,"agentic_index":null,"design_arena_best":null,"arena_text":1317.5796589492732,"arena_text_rank":265,"arena_text_rating_lower":1314.0300165249307,"arena_text_rating_upper":1321.1293013736156,"arena_text_vote_count":68705,"arena_text_date":"2026-10-15","arena_creative_writing":1293.8112796455557,"arena_creative_writing_rank":245,"arena_creative_writing_rating_lower":1286.8031395985604,"arena_creative_writing_rating_upper":1300.8194196925513,"arena_creative_writing_vote_count":10486,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","frequency_penalty","logit_bias","logprobs","prediction","presence_penalty","stop","temperature","top_logprobs","top_p","web_search_options"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4o-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-07-18","knowledge_cutoff":"2023-09","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.7,"coding_index":11.4,"agentic_index":null,"design_arena_best":null,"arena_text":1317.5796589492732,"arena_text_rank":265,"arena_text_rating_lower":1314.0300165249307,"arena_text_rating_upper":1321.1293013736156,"arena_text_vote_count":68705,"arena_text_date":"2026-10-15","arena_creative_writing":1293.8112796455557,"arena_creative_writing_rank":245,"arena_creative_writing_rating_lower":1286.8031395985604,"arena_creative_writing_rating_upper":1300.8194196925513,"arena_creative_writing_vote_count":10486,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-4o-mini:batch","name":"OpenAI: GPT-4o-mini (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","frequency_penalty","logit_bias","logprobs","prediction","presence_penalty","stop","temperature","top_logprobs","top_p","web_search_options"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4o-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2024-07-18","knowledge_cutoff":"2023-09","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.7,"coding_index":11.4,"agentic_index":null,"design_arena_best":null,"arena_text":1317.5796589492732,"arena_text_rank":265,"arena_text_rating_lower":1314.0300165249307,"arena_text_rating_upper":1321.1293013736156,"arena_text_vote_count":68705,"arena_text_date":"2026-10-15","arena_creative_writing":1293.8112796455557,"arena_creative_writing_rank":245,"arena_creative_writing_rating_lower":1286.8031395985604,"arena_creative_writing_rating_upper":1300.8194196925513,"arena_creative_writing_vote_count":10486,"arena_creative_writing_date":"2026-10-15"}},{"id":"google/gemma-2-27b-it","name":"Google: Gemma 2 27B","provider":"nextbit","provider_display":"NextBit","quantization":"int4","discount":0,"context_length":8192,"max_completion_tokens":2048,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","response_format","structured_outputs","repetition_penalty","seed"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.65,"output":0.65,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1289.5141560661143,"arena_text_rank":293,"arena_text_rating_lower":1286.1174752803583,"arena_text_rating_upper":1292.9108368518703,"arena_text_vote_count":75754,"arena_text_date":"2026-10-15","arena_creative_writing":1292.7947572985581,"arena_creative_writing_rank":249,"arena_creative_writing_rating_lower":1285.8991751660644,"arena_creative_writing_rating_upper":1299.6903394310518,"arena_creative_writing_vote_count":11429,"arena_creative_writing_date":"2026-10-15"}},{"id":"openai/gpt-4o:batch","name":"OpenAI: GPT-4o (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","frequency_penalty","logit_bias","logprobs","prediction","presence_penalty","stop","temperature","top_logprobs","top_p","web_search_options"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":1.25,"output":5,"cache_read":0.625,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4o","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2024-05-13","knowledge_cutoff":"2023-09","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":8.4,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":906,"win_rate":42.3,"rank":136},"arena_text":1346.1327118570525,"arena_text_rank":225,"arena_text_rating_lower":1342.6666387157807,"arena_text_rating_upper":1349.5987849983242,"arena_text_vote_count":112881,"arena_text_date":"2026-10-15","arena_creative_writing":1337.5936624648746,"arena_creative_writing_rank":193,"arena_creative_writing_rating_lower":1330.4173187854085,"arena_creative_writing_rating_upper":1344.7700061443406,"arena_creative_writing_vote_count":16599,"arena_creative_writing_date":"2026-10-15"}},{"id":"mistralai/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":65536,"max_completion_tokens":52428,"uptime_30m":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":6,"cache_read":0.19999999999999998,"cache_write":null},"org":"mistral","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-4-turbo:batch","name":"OpenAI: GPT-4 Turbo (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":4096,"uptime_30m":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","frequency_penalty","logit_bias","logprobs","presence_penalty","stop","temperature","top_logprobs","top_p"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":null,"pricing":{"input":5,"output":15,"cache_read":null,"cache_write":null},"org":"openai","lifecycle_status":"deprecated","modelsdev":{"base_url":null,"model_id":"gpt-4-turbo","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2023-11-06","knowledge_cutoff":"2023-12","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":6.7,"coding_index":21.5,"agentic_index":null,"design_arena_best":null,"arena_text":1324.5281327823136,"arena_text_rank":253,"arena_text_rating_lower":1320.6013929849275,"arena_text_rating_upper":1328.4548725796997,"arena_text_vote_count":98114,"arena_text_date":"2026-10-15","arena_creative_writing":1323.172395298996,"arena_creative_writing_rank":211,"arena_creative_writing_rating_lower":1315.3844704055596,"arena_creative_writing_rating_upper":1330.9603201924324,"arena_creative_writing_vote_count":14396,"arena_creative_writing_date":"2026-10-15"}},{"id":"mistralai/mistral-large","name":"Mistral Large","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":102400,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","response_format","structured_outputs","tools","tool_choice"],"supports_tool_choice":true,"supports_implicit_caching":true,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":2,"output":6,"cache_read":0.19999999999999998,"cache_write":null},"org":"mistral","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":5.8,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"openai/gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":4095,"max_completion_tokens":3685,"uptime_30m":null,"supported_parameters":["temperature","top_p","max_completion_tokens","tools","tool_choice","stop","frequency_penalty","presence_penalty","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":1,"output":2,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":16385,"max_completion_tokens":4096,"uptime_30m":null,"supported_parameters":["temperature","top_p","max_completion_tokens","tools","tool_choice","stop","frequency_penalty","presence_penalty","seed","logit_bias","logprobs","top_logprobs","response_format","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":3,"output":4,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":16385,"max_completion_tokens":4096,"uptime_30m":null,"supported_parameters":["seed","max_tokens","response_format","structured_outputs","tools","tool_choice","frequency_penalty","logit_bias","logprobs","presence_penalty","stop","temperature","top_logprobs","top_p"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":0,"pricing":{"input":3,"output":4,"cache_read":null,"cache_write":null},"org":"openai","open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"mancer/weaver","name":"Mancer: Weaver (alpha)","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":8000,"max_completion_tokens":6000,"uptime_30m":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","logprobs","top_logprobs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.39999999999999997,"output":0.75,"cache_read":null,"cache_write":null},"org":"mancer","zdr":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":6144,"max_completion_tokens":5529,"uptime_30m":null,"supported_parameters":["response_format","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.35,"output":0.65,"cache_read":null,"cache_write":null},"org":"undi95","zdr":true,"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","provider":"parasail","provider_display":"Parasail","quantization":"fp16","discount":0,"context_length":4096,"max_completion_tokens":3686,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.08,"output":0.11,"cache_read":null,"cache_write":null},"org":"gryphe","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2023-08-10","knowledge_cutoff":null,"description":"Llama 2 merge combining MythoLogic and Huginn for creative writing and roleplay","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://novita.ai/docs/guides/introduction","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":8192,"max_completion_tokens":7372,"uptime_30m":100,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","logit_bias","top_k","min_p","seed","top_a","response_format","logprobs","top_logprobs","structured_outputs"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":0.35,"output":0.6,"cache_read":null,"cache_write":null},"org":"gryphe","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2023-08-10","knowledge_cutoff":null,"description":"Llama 2 merge combining MythoLogic and Huginn for creative writing and roleplay","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://novita.ai/docs/guides/introduction","reasoning_options":null,"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"openai/gpt-4","name":"OpenAI: GPT-4","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":8191,"max_completion_tokens":4096,"uptime_30m":null,"supported_parameters":["temperature","top_p","max_completion_tokens","tools","tool_choice","stop","frequency_penalty","presence_penalty","seed","logit_bias","logprobs","top_logprobs","response_format"],"supports_tool_choice":true,"supports_implicit_caching":false,"max_prompt_tokens":null,"uptime_1d":100,"pricing":{"input":30,"output":60,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2023-11-06","knowledge_cutoff":"2023-11","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"license":null,"doc_url":"https://platform.openai.com/docs/models","reasoning_options":null,"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":6.7,"coding_index":21.5,"agentic_index":null,"design_arena_best":null,"arena_text":1324.5281327823136,"arena_text_rank":253,"arena_text_rating_lower":1320.6013929849275,"arena_text_rating_upper":1328.4548725796997,"arena_text_vote_count":98114,"arena_text_date":"2026-10-15","arena_creative_writing":1323.172395298996,"arena_creative_writing_rank":211,"arena_creative_writing_rating_lower":1315.3844704055596,"arena_creative_writing_rating_upper":1330.9603201924324,"arena_creative_writing_vote_count":14396,"arena_creative_writing_date":"2026-10-15"}},{"id":"mimo-v2.5","name":"mimo-v2.5","provider":"xiaomimimo","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":null},"org":"xiaomi","subscription":true,"max_completion_tokens":131072,"lifecycle_status":"deprecated","modelsdev":{"base_url":"https://api.xiaomimimo.com/v1","model_id":"mimo-v2.5","doc_url":"https://platform.xiaomimimo.com/#/docs","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"Open MiMo model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":null,"coding_index":56.8,"agentic_index":15.8,"design_arena_best":{"category":"website","elo":1265,"win_rate":53.6,"rank":35},"arena_text":1433.780160902417,"arena_text_rank":108,"arena_text_rating_lower":1429.557633161148,"arena_text_rating_upper":1438.002688643686,"arena_text_vote_count":47362,"arena_text_date":"2026-10-15","arena_creative_writing":1394.990883226929,"arena_creative_writing_rank":116,"arena_creative_writing_rating_lower":1387.2259701258565,"arena_creative_writing_rating_upper":1402.7557963280017,"arena_creative_writing_vote_count":7900,"arena_creative_writing_date":"2026-10-15"}},{"id":"mimo-v2.5-pro","name":"mimo-v2.5-pro","provider":"xiaomimimo","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.305,"output":2.61,"cache_read":0.0108,"cache_write":null},"org":"xiaomi","subscription":true,"max_completion_tokens":131072,"lifecycle_status":"deprecated","modelsdev":{"base_url":"https://api.xiaomimimo.com/v1","model_id":"mimo-v2.5-pro","doc_url":"https://platform.xiaomimimo.com/#/docs","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"benchmarks":{"intelligence_index":26,"coding_index":60.2,"agentic_index":21.3,"design_arena_best":{"category":"codecategories","elo":1266,"win_rate":51.7,"rank":35},"arena_text":1467.2561325712447,"arena_text_rank":49,"arena_text_rating_lower":1463.7152451466172,"arena_text_rating_upper":1470.7970199958725,"arena_text_vote_count":75721,"arena_text_date":"2026-10-15","arena_creative_writing":1433.903257618414,"arena_creative_writing_rank":67,"arena_creative_writing_rating_lower":1427.7056499079981,"arena_creative_writing_rating_upper":1440.10086532883,"arena_creative_writing_vote_count":14122,"arena_creative_writing_date":"2026-10-15"}},{"id":"mimo-v2.5-pro-ultraspeed","name":"mimo-v2.5-pro-ultraspeed","provider":"xiaomimimo","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":3.915,"output":7.83,"cache_read":0.0324,"cache_write":null},"org":"xiaomimimo","subscription":true,"max_completion_tokens":131072,"lifecycle_status":"deprecated","modelsdev":{"base_url":"https://api.xiaomimimo.com/v1","model_id":"mimo-v2.5-pro-ultraspeed","doc_url":"https://platform.xiaomimimo.com/#/docs","confidence":"high","source":"models.dev","release_date":"2026-06-08","knowledge_cutoff":"2024-12","description":"MiMo pro model for strong multimodal reasoning and agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null},{"id":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","provider":"makora","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.09,"output":0.195,"cache_read":0.0196,"cache_write":null},"org":"deepseek","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://portal.neuralwatt.com/docs","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.2,"agentic_index":22.2,"design_arena_best":{"category":"website","elo":1206,"win_rate":49.1,"rank":63},"arena_text":1435.6475480811423,"arena_text_rank":104,"arena_text_rating_lower":1431.6117385720809,"arena_text_rating_upper":1439.6833575902037,"arena_text_vote_count":51987,"arena_text_date":"2026-10-15","arena_creative_writing":1408.351388856729,"arena_creative_writing_rank":95,"arena_creative_writing_rating_lower":1400.836503394342,"arena_creative_writing_rating_upper":1415.8662743191164,"arena_creative_writing_vote_count":8582,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","provider":"makora","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.39,"output":2.79,"cache_read":0.301,"cache_write":null},"org":"deepseek","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.arcee.ai","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"gemma-4-26b-a4b","name":"Gemma-4-26B-A4B","provider":"makora","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.1,"output":0.34,"cache_read":0.034,"cache_write":null},"org":"makora","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1437.519731525164,"arena_text_rank":101,"arena_text_rating_lower":1430.082988387981,"arena_text_rating_upper":1444.956474662347,"arena_text_vote_count":6094,"arena_text_date":"2026-10-15","arena_creative_writing":1399.2858260617113,"arena_creative_writing_rank":112,"arena_creative_writing_rating_lower":1380.9697731856947,"arena_creative_writing_rating_upper":1417.601878937728,"arena_creative_writing_vote_count":1001,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.2-fp8","name":"GLM-5.2-FP8","provider":"makora","quantization":"fp8","discount":0,"context_length":980000,"pricing":{"input":0.94,"output":2.8,"cache_read":0.18,"cache_write":null},"org":"z-ai","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.2-nvfp4","name":"GLM-5.2-NVFP4","provider":"makora","quantization":"nvfp4","discount":0,"context_length":980000,"pricing":{"input":0.72,"output":2.38,"cache_read":0.12,"cache_write":null},"org":"z-ai","zdr":true,"subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":null},"org":"z-ai","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"glm-5.3-flash","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":41.8,"coding_index":71.5,"agentic_index":50.9,"design_arena_best":{"category":"3d","elo":1314,"win_rate":56.2,"rank":18},"arena_text":1473.8381537025502,"arena_text_rank":41,"arena_text_rating_lower":1468.9663672235586,"arena_text_rating_upper":1478.709940181542,"arena_text_vote_count":32925,"arena_text_date":"2026-10-15","arena_creative_writing":1433.6567070428632,"arena_creative_writing_rank":68,"arena_creative_writing_rating_lower":1425.4837598909164,"arena_creative_writing_rating_upper":1441.8296541948102,"arena_creative_writing_vote_count":6983,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.3","name":"GLM-5.3","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"glm-5.3","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-08-14","knowledge_cutoff":null,"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":31.7,"coding_index":74.8,"agentic_index":53.1,"design_arena_best":{"category":"3d","elo":1328,"win_rate":59.2,"rank":16},"arena_text":1478.538851947597,"arena_text_rank":28,"arena_text_rating_lower":1473.3104541772093,"arena_text_rating_upper":1483.7672497179851,"arena_text_vote_count":22543,"arena_text_date":"2026-10-15","arena_creative_writing":1453.2037886202456,"arena_creative_writing_rank":35,"arena_creative_writing_rating_lower":1443.8886671906848,"arena_creative_writing_rating_upper":1462.5189100498067,"arena_creative_writing_vote_count":5066,"arena_creative_writing_date":"2026-10-15"}},{"id":"glm-5.2","name":"GLM-5.2","provider":"opencode","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"glm-5.2","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","provider":"opencode","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":2,"output":10,"cache_read":0.2,"cache_write":2},"org":"moonshot","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"kimi-k3.1-pro","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-10-23","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":46,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1451,"win_rate":72.7,"rank":2}}},{"id":"kimi-k3","name":"Kimi K3","provider":"opencode","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3},"org":"moonshot","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"kimi-k3","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":76.2,"agentic_index":50,"design_arena_best":{"category":"3d","elo":1384,"win_rate":67,"rank":9},"arena_text":1487.071983223727,"arena_text_rank":18,"arena_text_rating_lower":1482.4881210528476,"arena_text_rating_upper":1491.6558453946066,"arena_text_vote_count":32795,"arena_text_date":"2026-10-15","arena_creative_writing":1461.2721978865138,"arena_creative_writing_rank":27,"arena_creative_writing_rating_lower":1453.0827008423319,"arena_creative_writing_rating_upper":1469.4616949306956,"arena_creative_writing_vote_count":6646,"arena_creative_writing_date":"2026-10-15"}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","provider":"opencode","quantization":null,"discount":0,"context_length":262000,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"moonshot","subscription":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"kimi-k2.7-code","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.8,"coding_index":60.8,"agentic_index":21,"design_arena_best":{"category":"website","elo":1262,"win_rate":51.2,"rank":37}}},{"id":"longcat-2.0","name":"LongCat-2.0","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"meituan","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"longcat-2.0","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-06-30","knowledge_cutoff":null,"description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":19.1,"coding_index":45.3,"agentic_index":14,"design_arena_best":null}},{"id":"step-5-preview","name":"Step 5 Preview","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1,"output":2.7,"cache_read":0.1,"cache_write":null},"org":"stepfun","subscription":true,"max_completion_tokens":65536,"max_prompt_tokens":1000000,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"step-5-preview","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-09-16","knowledge_cutoff":null,"description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.5,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1447.2701609595606,"arena_text_rank":84,"arena_text_rating_lower":1439.7616339961178,"arena_text_rating_upper":1454.7786879230032,"arena_text_vote_count":7116,"arena_text_date":"2026-10-15","arena_creative_writing":1403.2020336131102,"arena_creative_writing_rank":104,"arena_creative_writing_rating_lower":1387.2084544088364,"arena_creative_writing_rating_upper":1419.195612817384,"arena_creative_writing_vote_count":1517,"arena_creative_writing_date":"2026-10-15"}},{"id":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","provider":"opencode","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":null},"org":"xiaomi","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"mimo-v2.6-flash","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":null,"description":"MiMo Flash model for multimodal coding agents and long-context automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26.7,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1450.9317048216278,"arena_text_rank":77,"arena_text_rating_lower":1444.4428108493223,"arena_text_rating_upper":1457.4205987939336,"arena_text_vote_count":10917,"arena_text_date":"2026-10-15","arena_creative_writing":1390.3598176343207,"arena_creative_writing_rank":128,"arena_creative_writing_rating_lower":1376.634668474174,"arena_creative_writing_rating_upper":1404.0849667944674,"arena_creative_writing_vote_count":2109,"arena_creative_writing_date":"2026-10-15"}},{"id":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","provider":"opencode","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.435,"output":0.87,"cache_read":0.003625,"cache_write":null},"org":"xiaomi","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"mimo-v2.6-pro","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":null,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":29.9,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1335,"win_rate":58.4,"rank":7},"arena_text":1479.194755229377,"arena_text_rank":27,"arena_text_rating_lower":1469.827446672319,"arena_text_rating_upper":1488.5620637864351,"arena_text_vote_count":4075,"arena_text_date":"2026-10-15","arena_creative_writing":1444.679173566022,"arena_creative_writing_rank":52,"arena_creative_writing_rating_lower":1423.5979241643079,"arena_creative_writing_rating_upper":1465.760422967736,"arena_creative_writing_vote_count":793,"arena_creative_writing_date":"2026-10-15"}},{"id":"mimo-v2.5","name":"MiMo-V2.5","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":null},"org":"xiaomi","subscription":true,"max_completion_tokens":128000,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"mimo-v2.5","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo omni model for text, image, video, audio, and agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":56.8,"agentic_index":15.8,"design_arena_best":{"category":"website","elo":1265,"win_rate":53.6,"rank":35},"arena_text":1433.780160902417,"arena_text_rank":108,"arena_text_rating_lower":1429.557633161148,"arena_text_rating_upper":1438.002688643686,"arena_text_vote_count":47362,"arena_text_date":"2026-10-15","arena_creative_writing":1394.990883226929,"arena_creative_writing_rank":116,"arena_creative_writing_rating_lower":1387.2259701258565,"arena_creative_writing_rating_upper":1402.7557963280017,"arena_creative_writing_vote_count":7900,"arena_creative_writing_date":"2026-10-15"}},{"id":"mimo-v2.5-pro","name":"MiMo-V2.5-Pro","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.435,"output":0.87,"cache_read":0.003625,"cache_write":null},"org":"xiaomi","subscription":true,"max_completion_tokens":128000,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"mimo-v2.5-pro","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo pro model for strong multimodal reasoning and agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":26,"coding_index":60.2,"agentic_index":21.3,"design_arena_best":{"category":"codecategories","elo":1266,"win_rate":51.7,"rank":35},"arena_text":1467.2561325712447,"arena_text_rank":49,"arena_text_rating_lower":1463.7152451466172,"arena_text_rating_upper":1470.7970199958725,"arena_text_vote_count":75721,"arena_text_date":"2026-10-15","arena_creative_writing":1433.903257618414,"arena_creative_writing_rank":67,"arena_creative_writing_rating_lower":1427.7056499079981,"arena_creative_writing_rating_upper":1440.10086532883,"arena_creative_writing_vote_count":14122,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax-m3.1-flash","name":"MiniMax M3.1 Flash","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"minimax","subscription":true,"max_completion_tokens":512000,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"minimax-m3.1-flash","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-10-19","knowledge_cutoff":null,"description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"interleaved_reasoning":true},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":28.9,"coding_index":null,"agentic_index":null,"design_arena_best":null}},{"id":"minimax-m3","name":"MiniMax M3","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","subscription":true,"max_completion_tokens":131072,"context_price_tiers":[{"above_tokens":200000,"input":0.6,"output":2.4,"cache_read":0.12,"cache_write":null},{"above_tokens":512000,"input":0.6,"output":2.4,"cache_read":0.12,"cache_write":null}],"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"minimax-m3","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-06-01","knowledge_cutoff":"2025-01","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":18.7,"coding_index":58.6,"agentic_index":29.5,"design_arena_best":{"category":"website","elo":1256,"win_rate":51.6,"rank":41},"arena_text":1441.3155955735351,"arena_text_rank":96,"arena_text_rating_lower":1437.475817974704,"arena_text_rating_upper":1445.1553731723666,"arena_text_vote_count":63973,"arena_text_date":"2026-10-15","arena_creative_writing":1405.4560855918369,"arena_creative_writing_rank":101,"arena_creative_writing_rating_lower":1398.8326312174556,"arena_creative_writing_rating_upper":1412.0795399662184,"arena_creative_writing_vote_count":11713,"arena_creative_writing_date":"2026-10-15"}},{"id":"minimax-m3-(>-512k-tokens)","name":"MiniMax M3 (> 512K tokens)","provider":"opencode","quantization":null,"discount":0,"context_length":null,"pricing":{"input":0.6,"output":2.4,"cache_read":0.12,"cache_write":null},"org":"opencode","subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"muse-spark-1.3-contributor","name":"Muse Spark 1.3 Contributor","provider":"opencode","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.1,"output":0.2,"cache_read":0.002,"cache_write":null},"org":"meta","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"muse-spark-1.3-contributor","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-09-02","knowledge_cutoff":null,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","provider":"opencode","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.1,"output":0.2,"cache_read":0.002,"cache_write":null},"org":"meta","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"muse-spark-1.2-contributor","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-08-05","knowledge_cutoff":null,"description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen3.8-max","name":"Qwen3.8 Max","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"org":"qwen","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"qwen3.8-max","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-08-03","knowledge_cutoff":null,"description":"2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":45.4,"coding_index":76.2,"agentic_index":56,"design_arena_best":null,"arena_text":1482.3530183862679,"arena_text_rank":24,"arena_text_rating_lower":1477.3762943638942,"arena_text_rating_upper":1487.3297424086413,"arena_text_vote_count":27766,"arena_text_date":"2026-10-15","arena_creative_writing":1468.9997777918718,"arena_creative_writing_rank":19,"arena_creative_writing_rating_lower":1459.9936527553632,"arena_creative_writing_rating_upper":1478.0059028283804,"arena_creative_writing_vote_count":5471,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"org":"qwen","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"qwen3.8-flash","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-08-26","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","provider":"opencode","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5},"org":"qwen","subscription":true,"max_completion_tokens":65536,"context_price_tiers":[{"above_tokens":200000,"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5},{"above_tokens":256000,"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5}],"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"qwen3.7-plus","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-06-02","knowledge_cutoff":"2025-04","description":"Multimodal reasoning model for visual analysis, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.2,"coding_index":55.9,"agentic_index":17.5,"design_arena_best":{"category":"dataviz","elo":1279,"win_rate":51.3,"rank":22},"arena_text":1455.682715060256,"arena_text_rank":69,"arena_text_rating_lower":1451.3500504663698,"arena_text_rating_upper":1460.0153796541422,"arena_text_vote_count":42075,"arena_text_date":"2026-10-15","arena_creative_writing":1431.499455939465,"arena_creative_writing_rank":72,"arena_creative_writing_rating_lower":1423.8736889483803,"arena_creative_writing_rating_upper":1439.1252229305496,"arena_creative_writing_vote_count":7841,"arena_creative_writing_date":"2026-10-15"}},{"id":"qwen3.7-plus-(>-256k-tokens)","name":"Qwen3.7 Plus (> 256K tokens)","provider":"opencode","quantization":null,"discount":0,"context_length":null,"pricing":{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5},"org":"opencode","subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v4.1-flash:off-peak","name":"DeepSeek V4.1 Flash (Off-Peak)","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.15,"output":0.6,"cache_read":0.003,"cache_write":null},"org":"opencode","subscription":true,"max_completion_tokens":384000,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"deepseek-v4.1-flash","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"medium","source":"models.dev","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4.1-flash-(peak)","name":"DeepSeek V4.1 Flash (Peak)","provider":"opencode","quantization":null,"discount":0,"context_length":null,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"opencode","subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v4-pro:off-peak","name":"DeepSeek V4 Pro (Off-Peak)","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.66,"output":1.98,"cache_read":0.022,"cache_write":null},"org":"opencode","subscription":true,"max_completion_tokens":384000,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"deepseek-v4-pro","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"medium","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36,"coding_index":59.4,"agentic_index":26.3,"design_arena_best":{"category":"3d","elo":1251,"win_rate":56.8,"rank":32},"arena_text":1457.7921446281084,"arena_text_rank":64,"arena_text_rating_lower":1453.8943665565255,"arena_text_rating_upper":1461.6899226996911,"arena_text_vote_count":57594,"arena_text_date":"2026-10-15","arena_creative_writing":1445.993829345811,"arena_creative_writing_rank":47,"arena_creative_writing_rating_lower":1438.7294409074607,"arena_creative_writing_rating_upper":1453.2582177841612,"arena_creative_writing_vote_count":9726,"arena_creative_writing_date":"2026-10-15"}},{"id":"deepseek-v4-pro-(peak)","name":"DeepSeek V4 Pro (Peak)","provider":"opencode","quantization":null,"discount":0,"context_length":null,"pricing":{"input":1.32,"output":3.96,"cache_read":0.044,"cache_write":null},"org":"opencode","subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"hy4-preview","name":"Hy4 preview","provider":"opencode","quantization":null,"discount":0,"context_length":1024000,"pricing":{"input":0.834,"output":2.501,"cache_read":0.042,"cache_write":null},"org":"tencent","subscription":true,"max_completion_tokens":64000,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"hy4-preview","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-08-28","knowledge_cutoff":null,"description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"hy3","name":"Hy3","provider":"opencode","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.14,"output":0.58,"cache_read":0.035,"cache_write":null},"org":"tencent","subscription":true,"max_completion_tokens":128000,"max_prompt_tokens":192000,"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"hy3","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-07-06","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"interleaved_reasoning":null},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":25.3,"coding_index":58.8,"agentic_index":24.1,"design_arena_best":{"category":"website","elo":1180,"win_rate":41.3,"rank":76},"arena_text":1453.1921880349164,"arena_text_rank":74,"arena_text_rating_lower":1447.0448295263823,"arena_text_rating_upper":1459.3395465434508,"arena_text_vote_count":12208,"arena_text_date":"2026-10-15","arena_creative_writing":1421.8046324903116,"arena_creative_writing_rank":82,"arena_creative_writing_rating_lower":1409.2973161031023,"arena_creative_writing_rating_upper":1434.3119488775212,"arena_creative_writing_vote_count":2429,"arena_creative_writing_date":"2026-10-15"}},{"id":"grok-4.7","name":"Grok 4.7","provider":"opencode","quantization":null,"discount":0,"context_length":500000,"pricing":{"input":2,"output":6,"cache_read":0.5,"cache_write":null},"org":"xai","subscription":true,"max_completion_tokens":500000,"context_price_tiers":[{"above_tokens":200000,"input":4,"output":12,"cache_read":1,"cache_write":null}],"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"grok-4.7","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-09-21","knowledge_cutoff":"2026-05","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":35,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":52.7,"rank":15},"arena_text":1443.9789336394695,"arena_text_rank":89,"arena_text_rating_lower":1437.5593577926459,"arena_text_rating_upper":1450.3985094862933,"arena_text_vote_count":11591,"arena_text_date":"2026-10-15","arena_creative_writing":1423.757121376712,"arena_creative_writing_rank":78,"arena_creative_writing_rating_lower":1411.1481840860185,"arena_creative_writing_rating_upper":1436.3660586674052,"arena_creative_writing_vote_count":2589,"arena_creative_writing_date":"2026-10-15"}},{"id":"grok-4.7-(>-200k-tokens)","name":"Grok 4.7 (> 200K tokens)","provider":"opencode","quantization":null,"discount":0,"context_length":null,"pricing":{"input":4,"output":12,"cache_read":1,"cache_write":null},"org":"opencode","subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"gpt-6-luna","name":"GPT 6 Luna","provider":"opencode","quantization":null,"discount":0,"context_length":1050000,"pricing":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"org":"openai","subscription":true,"max_completion_tokens":128000,"max_prompt_tokens":922000,"context_price_tiers":[{"above_tokens":200000,"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25},{"above_tokens":272000,"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}],"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"gpt-6-luna","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-09-22","knowledge_cutoff":"2026-05-18","description":"OpenAI's most efficient model for focused, high-volume tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"uptime_1d":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":27.8,"coding_index":null,"agentic_index":null,"design_arena_best":null,"arena_text":1442.8129943072395,"arena_text_rank":91,"arena_text_rating_lower":1438.1883147148455,"arena_text_rating_upper":1447.4376738996334,"arena_text_vote_count":49617,"arena_text_date":"2026-10-15","arena_creative_writing":1410.0344781879853,"arena_creative_writing_rank":91,"arena_creative_writing_rating_lower":1402.9014608939249,"arena_creative_writing_rating_upper":1417.1674954820458,"arena_creative_writing_vote_count":11078,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-6-luna-(>-272k-tokens)","name":"GPT 6 Luna (> 272K tokens)","provider":"opencode","quantization":null,"discount":0,"context_length":null,"pricing":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25},"org":"opencode","subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"gpt-5.6-luna","name":"GPT 5.6 Luna","provider":"opencode","quantization":null,"discount":0,"context_length":1050000,"pricing":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"org":"openai","subscription":true,"max_completion_tokens":128000,"max_prompt_tokens":922000,"context_price_tiers":[{"above_tokens":200000,"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5},{"above_tokens":272000,"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}],"modelsdev":{"base_url":"https://opencode.ai/inference/go/openai/v1","model_id":"gpt-5.6-luna","doc_url":"https://opencode.ai/v2/docs/console/go/","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"license":null,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"interleaved_reasoning":null},"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"uptime_1d":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":37.3,"coding_index":71.4,"agentic_index":42.1,"design_arena_best":null,"arena_text":1452.5662458726235,"arena_text_rank":75,"arena_text_rating_lower":1448.2646893469653,"arena_text_rating_upper":1456.8678023982818,"arena_text_vote_count":41109,"arena_text_date":"2026-10-15","arena_creative_writing":1409.8692518077291,"arena_creative_writing_rank":92,"arena_creative_writing_rating_lower":1402.2779905913478,"arena_creative_writing_rating_upper":1417.4605130241107,"arena_creative_writing_vote_count":8603,"arena_creative_writing_date":"2026-10-15"}},{"id":"gpt-5.6-luna-(>-272k-tokens)","name":"GPT 5.6 Luna (> 272K tokens)","provider":"opencode","quantization":null,"discount":0,"context_length":null,"pricing":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5},"org":"opencode","subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"claude-haiku-5.5","name":"Claude Haiku 5.5","provider":"opencode","quantization":null,"discount":0,"context_length":null,"pricing":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"org":"anthropic","subscription":true,"open_weights":false,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":36.2,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1343,"win_rate":58.1,"rank":11}}},{"id":"claude-haiku-5.5-(>-100k-tokens)","name":"Claude Haiku 5.5 (> 100K tokens)","provider":"opencode","quantization":null,"discount":0,"context_length":null,"pricing":{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625},"org":"opencode","subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"gemini-4-argon-(50%-off)","name":"Gemini 4 Argon (50% off)","provider":"opencode","quantization":null,"discount":0,"context_length":null,"pricing":{"input":4,"output":20,"cache_read":0.2,"cache_write":null},"org":"opencode","subscription":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"umans-kimi-k2.7","name":"Umans Kimi K2.7 Code","provider":"umans","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"umans","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"umans-glm-5.2","name":"Umans GLM 5.2","provider":"umans","quantization":null,"discount":0,"context_length":405504,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"umans","zdr":true,"open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"intelligence_index":null,"coding_index":68.8,"agentic_index":38.4,"design_arena_best":{"category":"uicomponent","elo":1290,"win_rate":55.3,"rank":23},"arena_text":1475.8811079028058,"arena_text_rank":32,"arena_text_rating_lower":1471.702113628,"arena_text_rating_upper":1480.0601021776117,"arena_text_vote_count":49820,"arena_text_date":"2026-10-15","arena_creative_writing":1454.4616552353555,"arena_creative_writing_rank":33,"arena_creative_writing_rating_lower":1447.4154445604188,"arena_creative_writing_rating_upper":1461.507865910292,"arena_creative_writing_vote_count":9915,"arena_creative_writing_date":"2026-10-15"}},{"id":"umans-flash","name":"Umans Flash","provider":"umans","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.15,"output":1,"cache_read":0.05,"cache_write":0},"org":"umans","zdr":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://api.code.umans.ai/v1","model_id":"umans-flash","doc_url":"https://app.umans.ai/offers/code/docs","confidence":"high","source":"models.dev","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"glm-5.3-abliterated","name":"GLM 5.3 Abliterated","provider":"refuseless","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":2,"output":3,"cache_read":0.35,"cache_write":null},"org":"refuseless","open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"glm-5.3-flash-abliterated","name":"GLM 5.3 Flash Abliterated","provider":"refuseless","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.25,"output":0.8,"cache_read":0.15,"cache_write":null},"org":"refuseless","open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"qwen3.8-flash-next-abliterated","name":"Qwen3.8 Flash Next Abliterated","provider":"refuseless","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.18,"output":0.6,"cache_read":0.09,"cache_write":null},"org":"refuseless","open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v4.1-flash-abliterated","name":"DeepSeek V4.1 Flash Abliterated","provider":"refuseless","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.6,"output":1.6,"cache_read":0.15,"cache_write":null},"org":"refuseless","open_weights":null,"open_weights_source":null,"license":null,"supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null},{"id":"deepseek-v4.1-flash-fast","name":"DeepSeek V4.1 Flash 1017 (Safeguards)","provider":"refuseless","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.05,"output":0.15,"cache_read":0.004,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-09-10","knowledge_cutoff":"2025-05","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"license":null,"doc_url":"https://docs.baseten.co/inference/model-apis/overview","reasoning_options":[{"type":"effort","values":["none","high","max"]}],"interleaved_reasoning":true},"open_weights":true,"open_weights_source":"modelsdev","license":"MIT","supported_parameters":null,"supports_tool_choice":null,"supports_implicit_caching":null,"max_prompt_tokens":null,"uptime_1d":null,"context_price_tiers":null,"lifecycle_status":null,"benchmarks":{"arena_text":1474.6319979791695,"arena_text_rank":38,"arena_text_rating_lower":1468.4086018074258,"arena_text_rating_upper":1480.8553941509128,"arena_text_vote_count":12793,"arena_text_date":"2026-10-15","arena_creative_writing":1440.004011025788,"arena_creative_writing_rank":58,"arena_creative_writing_rating_lower":1427.6389056514847,"arena_creative_writing_rating_upper":1452.3691164000916,"arena_creative_writing_vote_count":2597,"arena_creative_writing_date":"2026-10-15"}}],"providers_meta":{"ember":{"privacy_policy_url":"https://www.embercloud.ai/privacy","terms_of_service_url":"https://www.embercloud.ai/terms","status_page_url":null,"headquarters":null,"datacenters":null,"source":"manual"},"hyper":{"privacy_policy_url":"https://hyper.charm.land/privacy","terms_of_service_url":"https://hyper.charm.land/terms","status_page_url":null,"headquarters":"US","datacenters":["US"],"retains_prompts":false,"may_train":false,"retention_days":30,"source":"manual","setup_env":["HYPER_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"makora":{"privacy_policy_url":"https://www.makora.com/privacy-policy","terms_of_service_url":"https://www.makora.com/terms-of-service","status_page_url":"https://status.makora.com","headquarters":"US","datacenters":["US"],"retains_prompts":false,"may_train":false,"retention_days":null,"source":"manual"},"synthetic":{"privacy_policy_url":"https://synthetic.new/policies/privacy","terms_of_service_url":"https://synthetic.new/policies/terms-of-service","status_page_url":null,"headquarters":"US","datacenters":["US"],"retains_prompts":false,"may_train":false,"retention_days":0,"source":"manual","setup_env":["SYNTHETIC_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"opencode":{"privacy_policy_url":"https://opencode.ai/legal/privacy-policy","terms_of_service_url":"https://opencode.ai/legal/terms-of-service","status_page_url":null,"headquarters":"US","datacenters":["US","EU","SG"],"retains_prompts":true,"may_train":false,"retention_days":null,"source":"manual","setup_env":["OPENCODE_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"xiaomimimo":{"privacy_policy_url":"https://privacy.mi.com/XiaomiMiMoPlatform/en_GB/","terms_of_service_url":"https://mimo.mi.com/docs/quick-start/terms/user-agreement","status_page_url":null,"headquarters":"NL","datacenters":["NL","SG"],"retains_prompts":true,"may_train":false,"retention_days":null,"source":"manual","setup_env":["XIAOMI_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"sference":{"privacy_policy_url":"https://sference.com/privacy","terms_of_service_url":"https://sference.com/terms","status_page_url":null,"headquarters":null,"datacenters":null,"retains_prompts":false,"may_train":false,"retention_days":null,"source":"manual"},"umans":{"privacy_policy_url":"https://app.umans.ai/offers/code/legal/privacy-policy","terms_of_service_url":"https://app.umans.ai/offers/code/legal/terms-of-use","status_page_url":"https://status.umans.ai/status","headquarters":null,"datacenters":null,"retains_prompts":false,"may_train":false,"retention_days":null,"source":"manual","setup_env":["UMANS_AI_CODING_PLAN_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"merius":{"privacy_policy_url":"https://tarmis.ai/privacy","terms_of_service_url":"https://tarmis.ai/terms","status_page_url":"https://status.merius.ai","headquarters":null,"datacenters":null,"retains_prompts":false,"may_train":false,"retention_days":null,"source":"manual"},"neuralwatt":{"privacy_policy_url":"https://portal.neuralwatt.com/privacy","terms_of_service_url":"https://portal.neuralwatt.com/terms","status_page_url":"https://neuralwatt.betteruptime.com","headquarters":null,"datacenters":null,"retains_prompts":false,"may_train":false,"retention_days":1,"source":"manual","setup_env":["NEURALWATT_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"aster":{"privacy_policy_url":"https://www.asterlab.ai/privacy","terms_of_service_url":"https://www.asterlab.ai/terms","status_page_url":null,"headquarters":"US","datacenters":null,"retains_prompts":false,"may_train":null,"retention_days":0,"source":"manual"},"arilo":{"privacy_policy_url":"https://arilo.id/privacy","terms_of_service_url":"https://arilo.id/terms","status_page_url":"https://arilo.id/status","headquarters":null,"datacenters":["HK","IE"],"retains_prompts":null,"may_train":false,"retention_days":null,"source":"manual"},"avian":{"privacy_policy_url":"https://avian.io/privacy","terms_of_service_url":"https://avian.io/terms","status_page_url":null,"headquarters":"US","datacenters":["US"],"retains_prompts":false,"may_train":false,"retention_days":0,"source":"manual"},"batchrate":{"privacy_policy_url":"https://batchrate.ai/privacy","terms_of_service_url":"https://batchrate.ai/terms","status_page_url":null,"headquarters":null,"datacenters":null,"retains_prompts":true,"may_train":false,"retention_days":30,"retention_note":"Input files deleted 7 days after the batch ends; output files after 30 days (can be shortened to 1 hour).","source":"manual"},"coralbricks":{"privacy_policy_url":"https://www.coralbricks.ai/privacy","terms_of_service_url":"https://www.coralbricks.ai/terms","status_page_url":"https://www.coralbricks.ai/status","headquarters":null,"datacenters":null,"retains_prompts":true,"may_train":false,"retention_days":30,"source":"manual","setup_env":["CORAL_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"singularity":{"privacy_policy_url":"https://www.singularityapi.dev/privacy","terms_of_service_url":"https://www.singularityapi.dev/terms","status_page_url":null,"headquarters":"US","datacenters":null,"retains_prompts":false,"may_train":false,"retention_days":0,"source":"manual"},"runinfra":{"privacy_policy_url":"https://runinfra.ai/privacy-policy","terms_of_service_url":"https://runinfra.ai/terms-of-service","status_page_url":"https://status.runinfra.ai/","headquarters":"US","datacenters":["US"],"retains_prompts":false,"may_train":false,"retention_days":1,"source":"manual","setup_env":["RUNINFRA_GATEWAY_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"runanywhere":{"privacy_policy_url":"https://runanywhere.ai/legal/privacy","terms_of_service_url":"https://runanywhere.ai/legal/terms","status_page_url":null,"headquarters":"US","datacenters":["US"],"retains_prompts":false,"may_train":false,"retention_days":0,"source":"manual"},"engy":{"privacy_policy_url":"https://engy.ai/privacy","terms_of_service_url":"https://engy.ai/terms","status_page_url":null,"headquarters":null,"datacenters":null,"retains_prompts":false,"may_train":false,"retention_days":0,"retention_note":"Gateway stores no request content. End-to-end ZDR requires the ZDR flag — unflagged requests may reach a worker run by an independent operator. Integrity audits (qwen3.6-35b-a3b only) keep response token IDs up to 30 days.","source":"manual"},"openscale":{"privacy_policy_url":"https://openscale.so/privacy","terms_of_service_url":"https://openscale.so/terms","status_page_url":null,"headquarters":"SG","datacenters":["SG"],"retains_prompts":false,"may_train":false,"retention_days":0,"retention_note":"Chat Completions and Messages are never stored. Responses API stores responses for 30 days unless store:false or account ZDR is enabled; that is not the calculator default path.","source":"manual"},"llmgateway":{"privacy_policy_url":"https://llmgateway.io/legal/privacy","terms_of_service_url":"https://llmgateway.io/legal/terms","status_page_url":null,"headquarters":null,"datacenters":null,"source":"manual"},"zro":{"privacy_policy_url":"https://zro.moonmath.ai/privacy","terms_of_service_url":"https://zro.moonmath.ai/terms","status_page_url":null,"headquarters":null,"datacenters":null,"may_train":false,"retention_days":null,"source":"manual"},"refuseless":{"privacy_policy_url":"https://refuseless.com/privacy","terms_of_service_url":"https://refuseless.com/terms","status_page_url":null,"headquarters":null,"datacenters":null,"retention_days":null,"source":"manual"},"ionstream":{"privacy_policy_url":"https://ionstream.ai/privacy-policy/","terms_of_service_url":"https://ionstream.ai/terms-and-conditions/","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"deepgram":{"privacy_policy_url":"https://deepgram.com/privacy","terms_of_service_url":"https://deepgram.com/terms","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"voyageai":{"privacy_policy_url":"https://www.voyageai.com/privacy","terms_of_service_url":"https://www.voyageai.com/tos","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"moonshotai":{"privacy_policy_url":"https://platform.moonshot.ai/docs/agreement/userprivacy","terms_of_service_url":"https://platform.moonshot.ai/docs/agreement/modeluse","status_page_url":null,"headquarters":"SG","datacenters":["SG"],"source":"openrouter"},"featherless":{"privacy_policy_url":"https://featherless.ai/privacy","terms_of_service_url":"https://featherless.ai/terms","status_page_url":"https://featherless.ai/status","headquarters":"US","datacenters":["US"],"source":"openrouter"},"arcee-ai":{"privacy_policy_url":null,"terms_of_service_url":null,"status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"particle-ai":{"privacy_policy_url":"https://particle.ai/privacy/","terms_of_service_url":"https://particle.ai/terms/","status_page_url":"https://status.particle.ai","headquarters":"US","datacenters":["US"],"source":"openrouter"},"pareto-alpha":{"privacy_policy_url":"https://paretoalphainference.com/privacy","terms_of_service_url":"https://paretoalphainference.com/terms","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"morph":{"privacy_policy_url":"https://morphllm.com/privacy","terms_of_service_url":"https://www.morphllm.com/privacy/tos","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter","setup_env":["MORPH_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"mistral":{"privacy_policy_url":"https://mistral.ai/terms/#privacy-policy","terms_of_service_url":"https://mistral.ai/terms/#terms-of-use","status_page_url":"https://status.mistral.ai/","headquarters":"FR","datacenters":null,"source":"openrouter","setup_env":["MISTRAL_API_KEY"],"ai_sdk_package":"@ai-sdk/mistral"},"ai21":{"privacy_policy_url":"https://www.ai21.com/privacy-policy/","terms_of_service_url":"https://www.ai21.com/terms-of-service/","status_page_url":"https://status.ai21.com/","headquarters":"IL","datacenters":null,"source":"openrouter"},"io-net":{"privacy_policy_url":"https://io.net/privacy","terms_of_service_url":"https://io.net/terms","status_page_url":"https://status.io.net/","headquarters":"US","datacenters":[],"source":"openrouter","setup_env":["IOINTELLIGENCE_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"black-forest-labs":{"privacy_policy_url":"https://bfl.ai/legal/privacy-policy","terms_of_service_url":"https://bfl.ai/legal/terms-of-service","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"recursive":{"privacy_policy_url":"https://recursive.com/legal/privacy-policy","terms_of_service_url":"https://recursive.com/legal/terms-of-use","status_page_url":null,"headquarters":"US","datacenters":null,"source":"openrouter"},"claude-on-aws":{"privacy_policy_url":"https://www.anthropic.com/legal/privacy","terms_of_service_url":"https://www.anthropic.com/legal/commercial-terms","status_page_url":"https://status.anthropic.com/","headquarters":"US","datacenters":null,"source":"openrouter"},"stepfun":{"privacy_policy_url":null,"terms_of_service_url":"https://platform.stepfun.ai/docs/en/agreement/userservice","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter","setup_env":["STEPFUN_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"darkbloom":{"privacy_policy_url":"https://www.darkbloom.dev/privacy.html","terms_of_service_url":"https://www.darkbloom.dev/terms.html","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"modal":{"privacy_policy_url":"https://modal.com/legal/privacy-policy","terms_of_service_url":"https://modal.com/legal/terms","status_page_url":"https://status.modal.com/","headquarters":"US","datacenters":[],"source":"openrouter","setup_env":["MODAL_PROXY_TOKEN"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"primalabs":{"privacy_policy_url":"https://www.primalabs.ai/privacy","terms_of_service_url":"https://www.primalabs.ai/terms","status_page_url":"https://status.primalabs.ai/","headquarters":"US","datacenters":null,"source":"openrouter"},"sail-research":{"privacy_policy_url":"https://www.sailresearch.com/privacy","terms_of_service_url":"https://www.sailresearch.com/terms","status_page_url":"https://status.sailresearch.com/","headquarters":"US","datacenters":[],"source":"openrouter"},"tencent":{"privacy_policy_url":"https://www.tencentcloud.com/en/document/product/1300/78952","terms_of_service_url":"https://www.tencentcloud.com/en/document/product/301/78869","status_page_url":"https://status.tencentcloud.com","headquarters":"CN","datacenters":["SG"],"source":"openrouter","setup_env":["TENCENT_TOKENHUB_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"perplexity":{"privacy_policy_url":"https://www.perplexity.ai/hub/legal/privacy-policy","terms_of_service_url":"https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service","status_page_url":"https://status.perplexity.ai/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["PERPLEXITY_API_KEY"],"ai_sdk_package":"@ai-sdk/perplexity"},"sambanova":{"privacy_policy_url":"https://sambanova.ai/privacy-policy","terms_of_service_url":"https://sambanova.ai/terms-and-conditions","status_page_url":"https://status.sambanova.ai/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["NOVA_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"stealth":{"privacy_policy_url":null,"terms_of_service_url":"https://openrouter.ai/terms/stealth","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"switchpoint":{"privacy_policy_url":null,"terms_of_service_url":null,"status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"ollama":{"privacy_policy_url":null,"terms_of_service_url":null,"status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"krea":{"privacy_policy_url":"https://www.krea.ai/privacy-policy","terms_of_service_url":"https://www.krea.ai/terms","status_page_url":null,"headquarters":"US","datacenters":[],"source":"openrouter"},"mara":{"privacy_policy_url":"https://www.mara.com/mara-legals/ai-policies#cloud-pp","terms_of_service_url":"https://www.mara.com/mara-legals/ai-policies#cloud-toc","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"amazon-nova":{"privacy_policy_url":null,"terms_of_service_url":null,"status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"cosine":{"privacy_policy_url":null,"terms_of_service_url":null,"status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"sourceful":{"privacy_policy_url":"https://www.sourceful.com/legal/privacy-policy","terms_of_service_url":"https://www.sourceful.com/legal/spring-terms-of-use","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"cloudflare":{"privacy_policy_url":"https://developers.cloudflare.com/workers-ai/privacy","terms_of_service_url":"https://www.cloudflare.com/service-specific-terms-developer-platform/#developer-platform-terms","status_page_url":"https://www.cloudflarestatus.com/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["CLOUDFLARE_ACCOUNT_ID","CLOUDFLARE_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"groq":{"privacy_policy_url":"https://groq.com/privacy-policy/","terms_of_service_url":"https://groq.com/terms-of-use/","status_page_url":"https://status.groq.com/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["GROQ_API_KEY"],"ai_sdk_package":"@ai-sdk/groq"},"mancer":{"privacy_policy_url":"https://mancer.tech/privacy","terms_of_service_url":"https://mancer.tech/terms","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"amazon-bedrock":{"privacy_policy_url":"https://aws.amazon.com/privacy","terms_of_service_url":"https://aws.amazon.com/service-terms/","status_page_url":"https://health.aws.amazon.com/health/status","headquarters":"US","datacenters":null,"source":"openrouter"},"crucible":{"privacy_policy_url":null,"terms_of_service_url":null,"status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"recraft":{"privacy_policy_url":null,"terms_of_service_url":null,"status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"decart":{"privacy_policy_url":"https://cogito.decart.ai/legal/privacy","terms_of_service_url":"https://cogito.decart.ai/legal/terms","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"dekallm":{"privacy_policy_url":"https://www.cloudeka.id/id/privacy-policy/","terms_of_service_url":"https://docs.cloudeka.ai/service-portal-ai/end-user-license-agreement","status_page_url":null,"headquarters":"ID","datacenters":["ID"],"source":"openrouter"},"minimax":{"privacy_policy_url":"https://www.minimax.io/platform/protocol/privacy-policy","terms_of_service_url":"https://www.minimax.io/platform/protocol/terms-of-service","status_page_url":null,"headquarters":"SG","datacenters":["US"],"source":"openrouter","setup_env":["MINIMAX_API_KEY"],"ai_sdk_package":"@ai-sdk/anthropic"},"modelrun":{"privacy_policy_url":"https://www.modular.com/legal/privacy","terms_of_service_url":"https://www.modular.com/legal/terms","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"perceptron":{"privacy_policy_url":"https://www.perceptron.inc/privacy-policy","terms_of_service_url":"https://www.perceptron.inc/terms-of-use","status_page_url":null,"headquarters":"US","datacenters":[],"source":"openrouter"},"poolside":{"privacy_policy_url":"https://poolside.ai/legal/privacy","terms_of_service_url":"http://poolside.ai/legal","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter","setup_env":["POOLSIDE_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"seed":{"privacy_policy_url":"https://docs.byteplus.com/en/docs/legal/docs-privacy-policy","terms_of_service_url":"https://docs.byteplus.com/en/docs/legal/docs-terms-of-service","status_page_url":null,"headquarters":"SG","datacenters":[],"source":"openrouter"},"inferact-vllm":{"privacy_policy_url":"https://inferact.ai/privacy-policy","terms_of_service_url":"https://inferact.ai/ortoc","status_page_url":null,"headquarters":"US","datacenters":["US","FI"],"source":"openrouter"},"coreweave":{"privacy_policy_url":"https://docs.coreweave.com/policies/terms-of-service/privacy-policy","terms_of_service_url":"https://docs.coreweave.com/policies/terms-of-service","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"runway":{"privacy_policy_url":"https://runwayml.com/privacy-policy","terms_of_service_url":"https://runwayml.com/terms-of-use","status_page_url":"https://status.runwayml.com","headquarters":"US","datacenters":null,"source":"openrouter"},"baidu":{"privacy_policy_url":"https://intl.cloud.baidu.com/en/doc/Agreements/s/Plr0fi68q-intl-en","terms_of_service_url":"https://intl.cloud.baidu.com/en/doc/Agreements/s/bmesahnjh-intl-en","status_page_url":null,"headquarters":"CN","datacenters":[],"source":"openrouter"},"modular":{"privacy_policy_url":"https://www.runmodelrun.com/privacy-policy.html","terms_of_service_url":"https://www.runmodelrun.com/TOS.html","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"cirrascale":{"privacy_policy_url":"https://www.cirrascale.com/privacy-policy","terms_of_service_url":"https://www.cirrascale.com/terms-of-service","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"baseten":{"privacy_policy_url":"https://www.baseten.co/privacy-policy","terms_of_service_url":"https://www.baseten.co/terms-and-conditions","status_page_url":"https://status.baseten.co/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["BASETEN_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"ambient":{"privacy_policy_url":null,"terms_of_service_url":null,"status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"crusoe":{"privacy_policy_url":"https://legal.crusoe.ai/open-router#cloud-privacy-policy","terms_of_service_url":"https://legal.crusoe.ai/open-router#managed-inference-tos-open-router","status_page_url":"https://status.crusoecloud.com/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["CRUSOE_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"inceptron":{"privacy_policy_url":"https://www.inceptron.io/privacy","terms_of_service_url":"https://www.inceptron.io/termsofservice","status_page_url":null,"headquarters":"SE","datacenters":["FI"],"source":"openrouter","setup_env":["INCEPTRON_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"cohere":{"privacy_policy_url":"https://cohere.com/privacy","terms_of_service_url":"https://cohere.com/terms-of-use","status_page_url":"https://status.cohere.ai/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["COHERE_API_KEY"],"ai_sdk_package":"@ai-sdk/cohere"},"deepseek":{"privacy_policy_url":"https://chat.deepseek.com/downloads/DeepSeek%20Privacy%20Policy.html","terms_of_service_url":"https://chat.deepseek.com/downloads/DeepSeek%20Terms%20of%20Use.html","status_page_url":"https://status.deepseek.com/","headquarters":"CN","datacenters":null,"source":"openrouter","setup_env":["DEEPSEEK_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"nex-agi":{"privacy_policy_url":"https://api.nex-agi.cn/privacy-policy","terms_of_service_url":null,"status_page_url":null,"headquarters":"CN","datacenters":["SG"],"source":"openrouter"},"reka":{"privacy_policy_url":"https://reka.ai/legal/privacy-policy","terms_of_service_url":"https://reka.ai/legal/terms-of-use","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"upstage":{"privacy_policy_url":"https://www.upstage.ai/privacy-policy","terms_of_service_url":"https://www.upstage.ai/terms-of-service","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter","setup_env":["UPSTAGE_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"thinkingmachines":{"privacy_policy_url":"https://thinkingmachines.ai/legal/tml-free-research-api-tier-privacy-notice.pdf","terms_of_service_url":"https://thinkingmachines.ai/legal/tml-free-research-api-tier-terms-of-service.pdf","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"xiaomi":{"privacy_policy_url":"https://platform.xiaomimimo.com/#/docs/terms/privacy-policy","terms_of_service_url":"https://platform.xiaomimimo.com/#/docs/terms/user-agreement","status_page_url":null,"headquarters":"CN","datacenters":["SG","NL"],"source":"openrouter","setup_env":["XIAOMI_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"nextbit":{"privacy_policy_url":"https://www.nextbit256.com/docs/privacy-policy","terms_of_service_url":"https://www.nextbit256.com/docs/terms-of-service","status_page_url":null,"headquarters":"ES","datacenters":["ES"],"source":"openrouter"},"databricks":{"privacy_policy_url":"https://www.databricks.com/legal/privacynotice","terms_of_service_url":"https://www.databricks.com/terms-of-use","status_page_url":"https://status.databricks.com","headquarters":"US","datacenters":null,"source":"openrouter"},"nvidia":{"privacy_policy_url":"https://www.nvidia.com/en-us/about-nvidia/privacy-policy/","terms_of_service_url":"https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"relace":{"privacy_policy_url":"https://www.relace.ai/privacy-policy","terms_of_service_url":"https://www.relace.ai/terms-of-use","status_page_url":"https://status.relace.ai","headquarters":null,"datacenters":[],"source":"openrouter"},"infermatic":{"privacy_policy_url":"https://infermatic.ai/privacy-policy/","terms_of_service_url":"https://infermatic.ai/terms-and-conditions/","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"streamlake":{"privacy_policy_url":"https://www.streamlake.ai/document/DOC/mgkci47q13qr66h9i54","terms_of_service_url":"https://www.streamlake.ai/document/DOC/mgkchnd89grpt1961fw","status_page_url":"https://status.streamlake.ai/","headquarters":"CN","datacenters":[],"source":"openrouter"},"assemblyai":{"privacy_policy_url":"https://www.assemblyai.com/legal/privacy-policy","terms_of_service_url":"https://www.assemblyai.com/legal/terms-of-service","status_page_url":"https://status.assemblyai.com","headquarters":null,"datacenters":["US"],"source":"openrouter"},"near-ai":{"privacy_policy_url":"https://near.ai/privacy-policy","terms_of_service_url":"https://near.ai/terms-of-service","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"typesafe":{"privacy_policy_url":"https://typesafe.ai/legal/privacy-policy","terms_of_service_url":"https://typesafe.ai/legal/terms","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"quiver":{"privacy_policy_url":null,"terms_of_service_url":null,"status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"clarifai":{"privacy_policy_url":"https://www.clarifai.com/company/privacy-policy","terms_of_service_url":"https://www.clarifai.com/company/terms","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter"},"z-ai":{"privacy_policy_url":"https://chat.z.ai/legal-agreement/privacy-policy","terms_of_service_url":"https://chat.z.ai/legal-agreement/terms-of-service","status_page_url":null,"headquarters":"SG","datacenters":["SG"],"source":"openrouter","setup_env":["ZHIPU_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"deepinfra":{"privacy_policy_url":"https://deepinfra.com/privacy","terms_of_service_url":"https://deepinfra.com/terms","status_page_url":"https://status.deepinfra.com/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["DEEPINFRA_API_KEY"],"ai_sdk_package":"@ai-sdk/deepinfra"},"unbiased":{"privacy_policy_url":"https://unbiased.ai/terms/#privacy-policy","terms_of_service_url":"https://unbiased.ai/terms/","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"heygen":{"privacy_policy_url":"https://www.heygen.com/privacy","terms_of_service_url":"https://www.heygen.com/terms","status_page_url":null,"headquarters":"US","datacenters":[],"source":"openrouter"},"tenstorrent":{"privacy_policy_url":"https://tenstorrent.com/privacy","terms_of_service_url":"https://console.tenstorrent.com/terms","status_page_url":"https://status.tenstorrent.com/","headquarters":"US","datacenters":["US"],"source":"openrouter"},"sakana":{"privacy_policy_url":"https://console.sakana.ai/privacy-policy","terms_of_service_url":"https://console.sakana.ai/terms-of-service","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter","setup_env":["SAKANA_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"fish-audio":{"privacy_policy_url":"https://fish.audio/privacy","terms_of_service_url":"https://fish.audio/terms","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"akashml":{"privacy_policy_url":"https://akashml.com/privacy","terms_of_service_url":"https://akashml.com/terms","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter"},"inflection":{"privacy_policy_url":"https://inflection.ai/privacy-policy","terms_of_service_url":"https://developers.inflection.ai/tos","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"scaledown":{"privacy_policy_url":"https://scaledown.ai/privacy","terms_of_service_url":"https://scaledown.ai/terms","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"respan":{"privacy_policy_url":"https://respan.ai/legal/privacy-policy","terms_of_service_url":"https://respan.ai/legal/terms-of-use","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"wafer":{"privacy_policy_url":"https://www.wafer.ai/privacy-policy","terms_of_service_url":"https://www.wafer.ai/terms","status_page_url":null,"headquarters":"US","datacenters":[],"source":"openrouter","setup_env":["WAFER_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"open-inference":{"privacy_policy_url":"https://www.openinference.ai/privacy","terms_of_service_url":"https://www.openinference.ai/terms","status_page_url":null,"headquarters":"US","datacenters":null,"source":"openrouter"},"xai":{"privacy_policy_url":"https://x.ai/legal/privacy-policy","terms_of_service_url":"https://x.ai/legal/terms-of-service-enterprise","status_page_url":"https://status.x.ai/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["XAI_API_KEY"],"ai_sdk_package":"@ai-sdk/xai"},"nebius":{"privacy_policy_url":"https://docs.nebius.com/legal/studio/privacy/","terms_of_service_url":"https://docs.nebius.com/legal/studio/terms-of-use/","status_page_url":null,"headquarters":"NL","datacenters":null,"source":"openrouter","setup_env":["NEBIUS_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"azure":{"privacy_policy_url":"https://www.microsoft.com/licensing/terms/product/PrivacyandSecurityTerms/MCA","terms_of_service_url":"https://learn.microsoft.com/en-us/legal/ai-code-of-conduct","status_page_url":"https://status.azure.com/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["AZURE_RESOURCE_NAME","AZURE_API_KEY"],"ai_sdk_package":"@ai-sdk/azure"},"primeintellect":{"privacy_policy_url":null,"terms_of_service_url":null,"status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"cerebras":{"privacy_policy_url":"https://www.cerebras.ai/privacy-policy","terms_of_service_url":"https://www.cerebras.ai/terms-of-service","status_page_url":"https://status.cerebras.ai/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["CEREBRAS_API_KEY"],"ai_sdk_package":"@ai-sdk/cerebras"},"elevenlabs":{"privacy_policy_url":"https://elevenlabs.io/privacy-policy","terms_of_service_url":"https://elevenlabs.io/terms-of-use","status_page_url":"https://status.elevenlabs.io","headquarters":null,"datacenters":null,"source":"openrouter"},"parasail":{"privacy_policy_url":"https://www.parasail.io/legal/privacy-policy","terms_of_service_url":"https://parasail.io/legal/terms-of-service","status_page_url":null,"headquarters":"US","datacenters":null,"source":"openrouter"},"aion-labs":{"privacy_policy_url":"https://www.aionlabs.ai/privacy-policy/","terms_of_service_url":"https://www.aionlabs.ai/terms/","status_page_url":null,"headquarters":"IL","datacenters":[],"source":"openrouter"},"inference-net":{"privacy_policy_url":"https://inference.net/privacy-policy","terms_of_service_url":"https://inference.net/terms-of-service","status_page_url":"https://status.inference.net","headquarters":"US","datacenters":null,"source":"openrouter"},"liquid":{"privacy_policy_url":"https://www.liquid.ai/privacy-policy","terms_of_service_url":"https://www.liquid.ai/terms-conditions","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter"},"meta":{"privacy_policy_url":"https://www.facebook.com/privacy/policy/","terms_of_service_url":"https://ai.developer.meta.com/legal/terms-of-service","status_page_url":null,"headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["META_MODEL_API_KEY"],"ai_sdk_package":"@ai-sdk/openai"},"siliconflow":{"privacy_policy_url":"https://docs.siliconflow.com/en/legals/privacy-policy","terms_of_service_url":"https://docs.siliconflow.com/en/legals/terms-of-service","status_page_url":null,"headquarters":"SG","datacenters":["US"],"source":"openrouter","setup_env":["SILICONFLOW_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"fake-provider":{"privacy_policy_url":null,"terms_of_service_url":null,"status_page_url":null,"headquarters":"US","datacenters":[],"source":"openrouter"},"phala":{"privacy_policy_url":"https://redpill.ai/privacy","terms_of_service_url":"https://redpill.ai/terms","status_page_url":"https://status.phala.network/","headquarters":"US","datacenters":null,"source":"openrouter"},"anthropic":{"privacy_policy_url":"https://www.anthropic.com/legal/privacy","terms_of_service_url":"https://www.anthropic.com/legal/commercial-terms","status_page_url":"https://status.anthropic.com/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["ANTHROPIC_API_KEY"],"ai_sdk_package":"@ai-sdk/anthropic"},"atlas-cloud":{"privacy_policy_url":"https://www.atlascloud.ai/privacy","terms_of_service_url":null,"status_page_url":null,"headquarters":"US","datacenters":null,"source":"openrouter"},"chutes":{"privacy_policy_url":"https://chutes.ai/privacy","terms_of_service_url":"https://chutes.ai/tos","status_page_url":null,"headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["CHUTES_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"google-ai-studio":{"privacy_policy_url":"https://cloud.google.com/terms/cloud-privacy-notice","terms_of_service_url":"https://cloud.google.com/terms/","status_page_url":null,"headquarters":"US","datacenters":null,"source":"openrouter"},"google-vertex":{"privacy_policy_url":"https://cloud.google.com/terms/cloud-privacy-notice","terms_of_service_url":"https://cloud.google.com/terms/","status_page_url":"https://status.cloud.google.com/products/sdXM79fz1FS6ekNpu37K/history","headquarters":"US","datacenters":null,"source":"openrouter"},"venice":{"privacy_policy_url":"https://venice.ai/legal/privacy-policy","terms_of_service_url":"https://venice.ai/legal/tos","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter","setup_env":["VENICE_API_KEY"],"ai_sdk_package":"venice-ai-sdk-provider"},"openai":{"privacy_policy_url":"https://openai.com/policies/privacy-policy/","terms_of_service_url":"https://openai.com/policies/row-terms-of-use/","status_page_url":"https://status.openai.com/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["OPENAI_API_KEY"],"ai_sdk_package":"@ai-sdk/openai"},"together":{"privacy_policy_url":"https://www.together.ai/privacy","terms_of_service_url":"https://www.together.ai/terms-of-service","status_page_url":"https://status.together.ai/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["TOGETHER_API_KEY"],"ai_sdk_package":"@ai-sdk/togetherai"},"friendli":{"privacy_policy_url":"https://friendli.ai/privacypolicy","terms_of_service_url":"https://friendli.ai/terms-of-service","status_page_url":"https://status.friendli.ai/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["FRIENDLI_TOKEN"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"inception":{"privacy_policy_url":"https://www.inceptionlabs.ai/terms#privacy-policy","terms_of_service_url":"https://www.inceptionlabs.ai/terms","status_page_url":null,"headquarters":null,"datacenters":null,"source":"openrouter","setup_env":["INCEPTION_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"gmicloud":{"privacy_policy_url":"https://docs.gmicloud.ai/privacy","terms_of_service_url":"https://www.gmicloud.ai/terms-and-conditions","status_page_url":null,"headquarters":"US","datacenters":["US"],"source":"openrouter","setup_env":["GMICLOUD_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"fireworks":{"privacy_policy_url":"https://fireworks.ai/privacy-policy","terms_of_service_url":"https://fireworks.ai/terms-of-service","status_page_url":"https://status.fireworks.ai/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["FIREWORKS_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"alibaba":{"privacy_policy_url":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-privacy-policy","terms_of_service_url":"https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0","status_page_url":"https://status.alibabacloud.com/","headquarters":"SG","datacenters":["SG","CN"],"source":"openrouter","setup_env":["DASHSCOPE_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"digitalocean":{"privacy_policy_url":"https://www.digitalocean.com/legal/privacy-policy","terms_of_service_url":"https://www.digitalocean.com/legal/terms-of-service-agreement","status_page_url":null,"headquarters":"US","datacenters":[],"source":"openrouter","setup_env":["DIGITALOCEAN_ACCESS_TOKEN"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"novita":{"privacy_policy_url":"https://novita.ai/legal/privacy-policy","terms_of_service_url":"https://novita.ai/legal/terms-of-service","status_page_url":"https://status.novita.ai/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["NOVITA_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"embercloud":{"privacy_policy_url":"https://www.embercloud.ai/privacy","terms_of_service_url":"https://www.embercloud.ai/terms","status_page_url":null,"headquarters":null,"datacenters":null,"source":"manual"},"arilo.id":{"privacy_policy_url":"https://arilo.id/privacy","terms_of_service_url":"https://arilo.id/terms","status_page_url":"https://arilo.id/status","headquarters":null,"datacenters":["HK","IE"],"retains_prompts":null,"may_train":false,"retention_days":null,"source":"manual"},"arilo-id":{"privacy_policy_url":"https://arilo.id/privacy","terms_of_service_url":"https://arilo.id/terms","status_page_url":"https://arilo.id/status","headquarters":null,"datacenters":["HK","IE"],"retains_prompts":null,"may_train":false,"retention_days":null,"source":"manual"},"z.ai":{"privacy_policy_url":"https://chat.z.ai/legal-agreement/privacy-policy","terms_of_service_url":"https://chat.z.ai/legal-agreement/terms-of-service","status_page_url":null,"headquarters":"SG","datacenters":["SG"],"source":"openrouter","setup_env":["ZHIPU_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"sakana ai":{"privacy_policy_url":"https://console.sakana.ai/privacy-policy","terms_of_service_url":"https://console.sakana.ai/terms-of-service","status_page_url":null,"headquarters":null,"datacenters":[],"source":"openrouter","setup_env":["SAKANA_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"aster labs":{"privacy_policy_url":"https://www.asterlab.ai/privacy","terms_of_service_url":"https://www.asterlab.ai/terms","status_page_url":null,"headquarters":"US","datacenters":null,"retains_prompts":false,"may_train":null,"retention_days":0,"source":"manual"},"singularityapi":{"privacy_policy_url":"https://www.singularityapi.dev/privacy","terms_of_service_url":"https://www.singularityapi.dev/terms","status_page_url":null,"headquarters":"US","datacenters":null,"retains_prompts":false,"may_train":false,"retention_days":0,"source":"manual"},"singularity api":{"privacy_policy_url":"https://www.singularityapi.dev/privacy","terms_of_service_url":"https://www.singularityapi.dev/terms","status_page_url":null,"headquarters":"US","datacenters":null,"retains_prompts":false,"may_train":false,"retention_days":0,"source":"manual"},"run infra":{"privacy_policy_url":"https://runinfra.ai/privacy-policy","terms_of_service_url":"https://runinfra.ai/terms-of-service","status_page_url":"https://status.runinfra.ai/","headquarters":"US","datacenters":["US"],"retains_prompts":false,"may_train":false,"retention_days":1,"source":"manual","setup_env":["RUNINFRA_GATEWAY_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"wally cloud":{"privacy_policy_url":"https://runanywhere.ai/legal/privacy","terms_of_service_url":"https://runanywhere.ai/legal/terms","status_page_url":null,"headquarters":"US","datacenters":["US"],"retains_prompts":false,"may_train":false,"retention_days":0,"source":"manual"},"wally":{"privacy_policy_url":"https://runanywhere.ai/legal/privacy","terms_of_service_url":"https://runanywhere.ai/legal/terms","status_page_url":null,"headquarters":"US","datacenters":["US"],"retains_prompts":false,"may_train":false,"retention_days":0,"source":"manual"},"open scale":{"privacy_policy_url":"https://openscale.so/privacy","terms_of_service_url":"https://openscale.so/terms","status_page_url":null,"headquarters":"SG","datacenters":["SG"],"retains_prompts":false,"may_train":false,"retention_days":0,"retention_note":"Chat Completions and Messages are never stored. Responses API stores responses for 30 days unless store:false or account ZDR is enabled; that is not the calculator default path.","source":"manual"},"coral bricks":{"privacy_policy_url":"https://www.coralbricks.ai/privacy","terms_of_service_url":"https://www.coralbricks.ai/terms","status_page_url":"https://www.coralbricks.ai/status","headquarters":null,"datacenters":null,"retains_prompts":true,"may_train":false,"retention_days":30,"source":"manual","setup_env":["CORAL_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"},"inference.net":{"privacy_policy_url":"https://inference.net/privacy-policy","terms_of_service_url":"https://inference.net/terms-of-service","status_page_url":"https://status.inference.net","headquarters":"US","datacenters":null,"source":"openrouter"},"nex agi":{"privacy_policy_url":"https://api.nex-agi.cn/privacy-policy","terms_of_service_url":null,"status_page_url":null,"headquarters":"CN","datacenters":["SG"],"source":"openrouter"},"x-ai":{"privacy_policy_url":"https://x.ai/legal/privacy-policy","terms_of_service_url":"https://x.ai/legal/terms-of-service-enterprise","status_page_url":"https://status.x.ai/","headquarters":"US","datacenters":null,"source":"openrouter","setup_env":["XAI_API_KEY"],"ai_sdk_package":"@ai-sdk/xai"},"umans ai":{"privacy_policy_url":"https://app.umans.ai/offers/code/legal/privacy-policy","terms_of_service_url":"https://app.umans.ai/offers/code/legal/terms-of-use","status_page_url":"https://status.umans.ai/status","headquarters":null,"datacenters":null,"retains_prompts":false,"may_train":false,"retention_days":null,"source":"manual","setup_env":["UMANS_AI_CODING_PLAN_API_KEY"],"ai_sdk_package":"@ai-sdk/openai-compatible"}}}