Baseten LLM API pricing
Every model Baseten serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first, with models Baseten lists no paid price for at the end. Listed prices from LiteLLM, OpenRouter and Vercel.
Models served
27
on this provider
Cheapest input
$0.10
per 1M tokens
Cheapest output
$0.26
per 1M tokens
Max context
1M
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
| Model ID | |||||
|---|---|---|---|---|---|
| gpt-oss-120b | OpenAI | 131K | $0.10 | $0.50 | baseten/openai/gpt-oss-120b |
| DeepSeek V4 Flash 0731 | DeepSeek | 1M | $0.13 | $0.26 | baseten/deepseek-ai/DeepSeek-V4-Flash-0731 |
| GLM 5.3 Flash | Zhipu | 1M | $0.15 | $0.50 | baseten/zai-org/GLM-5.3-Flash |
| DeepSeek V4.1 Flash | DeepSeek | 1M | $0.30 | $1.20 | baseten/deepseek-ai/DeepSeek-V4.1-Flash |
| MiniMax M2.5 | MiniMax | 1M | $0.30 | $1.20 | baseten/MiniMaxAI/MiniMax-M2.5 |
| Nemotron 120B A12b | NVIDIA | n/a | $0.30 | $0.75 | baseten/nvidia/Nemotron-120B-A12B |
| DeepSeek V3.1 | DeepSeek | 164K | $0.50 | $1.50 | baseten/deepseek-ai/DeepSeek-V3.1 |
| Inkling Small | Thinking Machines | 1M | $0.50 | $1.20 | baseten/thinkingmachines/inkling-small |
| DeepSeek V4.1 Flash Fast | DeepSeek | 1M | $0.60 | $2.40 | baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast |
| GLM 4.6 | Zhipu | 205K | $0.60 | $2.20 | baseten/zai-org/GLM-4.6 |
| GLM 4.7 | Zhipu | 205K | $0.60 | $2.20 | baseten/zai-org/GLM-4.7 |
| Kimi K2 Instruct 0905 | Moonshot | 262K | $0.60 | $2.50 | baseten/moonshotai/Kimi-K2-Instruct-0905 |
| Kimi K2 Thinking | Moonshot | 262K | $0.60 | $2.50 | baseten/moonshotai/Kimi-K2-Thinking |
| Kimi K2.5 | Moonshot | 262K | $0.60 | $3.00 | baseten/moonshotai/Kimi-K2.5 |
| Nvidia Nemotron 3 Ultra 550B A55b | NVIDIA | 262K | $0.60 | $2.40 | baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B |
| DeepSeek V3 0324 | DeepSeek | 164K | $0.77 | $0.77 | baseten/deepseek-ai/DeepSeek-V3-0324 |
| GLM 5 | Zhipu | 1M | $0.95 | $3.15 | baseten/zai-org/GLM-5 |
| Kimi K2.6 | Moonshot | 262K | $0.95 | $4.00 | baseten/moonshotai/Kimi-K2.6 |
| Kimi K2.7 Code | Moonshot | 262K | $0.95 | $4.00 | baseten/moonshotai/Kimi-K2.7-Code |
| Inkling | Thinking Machines | 1M | $1.00 | $4.05 | baseten/thinkingmachines/inkling |
| DeepSeek V4 Pro 0813 | DeepSeek | 1M | $1.32 | $3.96 | baseten/deepseek-ai/DeepSeek-V4-Pro-0813 |
| GLM 5.2 | Zhipu | 1M | $1.40 | $4.40 | baseten/zai-org/GLM-5.2 |
| GLM 5.3 | Zhipu | 1M | $1.40 | $4.40 | baseten/zai-org/GLM-5.3 |
| DeepSeek V4 Pro 0423 | DeepSeek | 1M | $1.74 | $3.48 | baseten/deepseek-ai/DeepSeek-V4-Pro |
| GLM 5.2 Fast | Zhipu | 1M | $2.10 | $6.60 | baseten/zai-org/GLM-5.2-Fast |
| GLM 5.3 Fast | Zhipu | 1M | $2.10 | $6.60 | baseten/zai-org/GLM-5.3-Fast |
| Kimi K3 | Moonshot | 1M | $3.00 | $15.00 | baseten/moonshotai/Kimi-K3 |
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI