Coreweave pricing overview
TokenWatch tracks 22 text, 0 image, and 0 video model records for this provider. TokenWatch does not have a provider-wide zero-retention verdict for this page.
Cheapest input price: gpt-oss-20b at $0.030 per million input tokens and $0.130 per million output tokens. 22 of 22 text models publish a cache-read price; 22 carry a zero-data-retention tag.
Coreweave text-model pricing
Text offerings ranked by the Agentic workload mix (2.5% input, 97% cached input, 0.5% output). Change the calculator mix for a workload-specific estimate.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| deepseek | coreweave | DeepSeek: DeepSeek V4.1 Flash | $0.130 | $0.650 | $0.0020 | $0.0084 |
| ibm | coreweave | IBM: Granite 4.2 8B | $0.060 | $0.150 | $0.015 | $0.017 |
| z-ai | coreweave | Z.ai: GLM 5.3 Flash | $0.120 | $0.380 | $0.020 | $0.024 |
| nvidia | coreweave | NVIDIA: Nemotron 3.5 Super VL | $0.150 | $0.500 | $0.020 | $0.026 |
| openai | coreweave | OpenAI: gpt-oss-20b | $0.030 | $0.130 | $0.030 | $0.030 |
| openai | coreweave | OpenAI: gpt-oss-120b | $0.030 | $0.170 | $0.030 | $0.031 |
| nvidia | coreweave | NVIDIA: Nemotron 3.5 Lightning | $0.070 | $0.200 | $0.040 | $0.042 |
| reflection | coreweave | Reflection: Beam 1.0 501B A23B | $0.300 | $1.00 | $0.040 | $0.051 |
| coreweave | Google: Gemma 4 26B A4B | $0.100 | $0.300 | $0.050 | $0.052 | |
| qwen | coreweave | Qwen: Qwen3.6 35B A3B | $0.100 | $0.950 | $0.050 | $0.056 |
| minimax | coreweave | MiniMax: MiniMax M3 | $0.230 | $0.960 | $0.050 | $0.059 |
| deepseek | coreweave | DeepSeek: DeepSeek V4 Flash 0731 | $0.130 | $0.280 | $0.070 | $0.073 |
| deepseek | coreweave | DeepSeek: DeepSeek V4 Pro 0813 | $1.31 | $3.96 | $0.044 | $0.095 |
| coreweave | Google: Gemma 4 31B | $0.100 | $0.340 | $0.100 | $0.101 | |
| moonshot | coreweave | MoonshotAI: Kimi K2.7 Code | $0.600 | $3.00 | $0.120 | $0.146 |
| z-ai | coreweave | Z.ai: GLM 5.2 | $0.620 | $2.42 | $0.140 | $0.163 |
| qwen | coreweave | Qwen: Qwen3.8 27B | $0.400 | $3.00 | $0.150 | $0.170 |
| moonshot | coreweave | MoonshotAI: Kimi K2.6 | $0.650 | $3.41 | $0.150 | $0.179 |
| meta | coreweave | Meta: Llama 3.1 8B Instruct | $0.220 | $0.220 | $0.220 | $0.220 |
| z-ai | coreweave | Z.ai: GLM 5.3 | $1.20 | $4.00 | $0.190 | $0.234 |
| deepseek | coreweave | DeepSeek: DeepSeek V3.1 | $0.550 | $1.65 | $0.550 | $0.555 |
| meta | coreweave | Meta: Llama 3.3 70B Instruct | $0.710 | $0.710 | $0.710 | $0.710 |
Catalog snapshot 2026-10-29 from direct-provider APIs, OpenRouter endpoint data, and maintained fallbacks. See the sources and calculation rules; verify rates on the provider's official pricing page before committing spend.