Baseten pricing overview
TokenWatch tracks 16 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-120b at $0.100 per million input tokens and $0.500 per million output tokens. 16 of 16 text models publish a cache-read price; 13 carry a zero-data-retention tag.
Baseten 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 | baseten | DeepSeek: DeepSeek V4.1 Flash 1017 | $0.300 | $1.20 | $0.0070 | $0.020 |
| deepseek | baseten | DeepSeek: DeepSeek V4.1 Flash | $0.300 | $1.20 | $0.0070 | $0.020 |
| deepseek | baseten | DeepSeek: DeepSeek V4 Flash 0731 | $0.130 | $0.260 | $0.028 | $0.032 |
| z-ai | baseten | Z.ai: GLM 5.3 Flash | $0.150 | $0.500 | $0.030 | $0.035 |
| deepseek | baseten | DeepSeek: DeepSeek V4.1 Flash (fast) | $0.600 | $2.40 | $0.014 | $0.041 |
| nvidia | baseten | NVIDIA: Nemotron 3.5 Super VL | $0.200 | $0.500 | $0.040 | $0.046 |
| reflection | baseten | Reflection: Beam 1.0 501B A23B | $0.400 | $1.20 | $0.040 | $0.055 |
| openai | baseten | OpenAI: gpt-oss-120b | $0.100 | $0.500 | $0.100 | $0.102 |
| nvidia | baseten | NVIDIA: Nemotron 3 Ultra | $0.600 | $2.40 | $0.120 | $0.143 |
| deepseek | baseten | DeepSeek: DeepSeek V4 Pro 0813 | $1.32 | $3.96 | $0.132 | $0.181 |
| z-ai | baseten | Z.ai: GLM 5.3 | $1.40 | $4.40 | $0.140 | $0.193 |
| z-ai | baseten | Z.ai: GLM 5.2 | $1.40 | $4.40 | $0.140 | $0.193 |
| meta | baseten | Meta: Muse Spark Open | $1.25 | $4.25 | $0.150 | $0.198 |
| z-ai | baseten | Z.ai: GLM 5.3 (fast) | $2.10 | $6.60 | $0.210 | $0.289 |
| z-ai | baseten | Z.ai: GLM 5.2 (fast) | $2.10 | $6.60 | $0.210 | $0.289 |
| moonshot | baseten | MoonshotAI: Kimi K3 | $3.00 | $15.00 | $0.300 | $0.441 |
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.