Baseten API pricing
8 models · USD per 1M tokens · verified 2026-10-23
Baseten serves 8 of the models we track, 8 of them open-weights. The cheapest is DeepSeek V4 Flash 0731 at $0.13 input and $0.26 output per million tokens. For 1 of these models, Baseten is the cheapest tracked host.
// models on Baseten
| model | lab | in $/1M | out $/1M | ctx | vs best price |
|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | DeepSeek | $0.13 | $0.26 | 1.05M | +80.6% |
| GPT OSS 120B | OpenAI | $0.10 | $0.50 | 131.1K | +184.5% |
| GLM-5.3-FlashX BEST | Z.AI (Zhipu) | $0.15 | $0.50 | 1M | −59.7% |
| DeepSeek V4.1 Flash | DeepSeek | $0.30 | $1.20 | 1.05M | +75% |
| DeepSeek V4 Pro (0813) | DeepSeek | $1.32 | $3.96 | 1.05M | +100% |
| GLM-5.2 | Z.AI (Zhipu) | $1.40 | $4.40 | 1M | best |
| GLM-5.3 | Z.AI (Zhipu) | $1.40 | $4.40 | 1M | best |
| Kimi K3 | Moonshot AI | $3.00 | $15.00 | 1.05M | best |
// how to read this page
Prices are Baseten's base-tier list prices per million tokens. "vs best price" compares Baseten's blended price (3 × input + output) / 4 with the lowest price we track for the same model, whether it comes from the lab's own API or another host. Open each model for its full price history and every host that serves it.