Baseten API pricing

10 models · USD per 1M tokens · verified 2026-11-14

Baseten serves 10 of the models we track, 10 of them open-weights. The cheapest is DeepSeek V4 Flash 0731 at $0.13 input and $0.26 output per million tokens. For 2 of these models, Baseten is the cheapest tracked host.

// models on Baseten

modellabin $/1Mout $/1Mctxvs best price
DeepSeek V4 Flash 0731DeepSeek$0.13$0.261.05M+80.6%
GPT OSS 120BOpenAI$0.10$0.50131.1K+184.5%
GLM-5.3-Flash BESTZ.AI (Zhipu)$0.15$0.501Mbest
DeepSeek V4.1 FlashDeepSeek$0.30$1.201.05M+75%
DeepSeek V4.1 Flash 1017DeepSeek$0.30$1.201.05M+100%
DeepSeek V4 Pro (0813)DeepSeek$1.32$3.961.05M+100%
GLM-5.2Z.AI (Zhipu)$1.40$4.401Mbest
GLM-5.3Z.AI (Zhipu)$1.40$4.401Mbest
Kimi K3.1 Pro BESTMoonshot AI$2.00$10.001.05Mbest
Kimi K3Moonshot AI$3.00$15.001.05Mbest

// 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.