LiteLLMModels

Baseten model pricing

As of October 10, 2026, 26 Baseten models are available through LiteLLM. The most recently added are DeepSeek V4.1 Flash Fast, GLM 5p3 Fast, DeepSeek V4.1 Flash. Prices below are Baseten's list prices.

How to call Baseten with LiteLLM

Baseten models

ModelLabPriceContextProvidersAdded
DeepSeek V4.1 Flash FastDeepSeek$0.60 / $2.40 per 1M tokens1M1Sep 2026
GLM 5p3 FastZ.ai$2.10 / $6.60 per 1M tokens1M2Sep 2026
DeepSeek V4.1 FlashDeepSeek$0.30 / $1.20 per 1M tokens1M8Sep 2026
GLM 5.3Z.ai$1.40 / $4.40 per 1M tokens1M12Aug 2026
GLM 5.3 FlashZ.ai$0.15 / $0.50 per 1M tokens1M11Aug 2026
Nvidia Nemotron 3 Ultra 550B A55BNVIDIA$0.60 / $2.40 per 1M tokens203K3Aug 2026
Inkling–$1 / $4.05 per 1M tokens1M4Aug 2026
Inkling Small–$0.50 / $1.20 per 1M tokens1M2Aug 2026
GLM 5p2 FastZ.ai$2.10 / $6.60 per 1M tokens1M2Aug 2026
Kimi K3Moonshot AI$3 / $15 per 1M tokens1M13Aug 2026
DeepSeek V4 FlashDeepSeek$0.13 / $0.26 per 1M tokens1M22Jun 2026
DeepSeek V4 ProDeepSeek$1.32 / $3.96 per 1M tokens1M17Jun 2026
GLM 5.2Z.ai$1.40 / $4.40 per 1M tokens1M19Jun 2026
Kimi K2.7 CodeMoonshot AI$0.95 / $4 per 1M tokens262K14Jun 2026
Kimi K2.6Moonshot AI$0.95 / $4 per 1M tokens262K13Apr 2026
Nemotron 120B A12BNVIDIA$0.30 / $0.75 per 1M tokens–1Apr 2026
GLM 5Z.ai$0.95 / $3.15 per 1M tokens200K7Feb 2026
Kimi K2.5Moonshot AI$0.60 / $3 per 1M tokens256K8Feb 2026
MiniMax M2.5MiniMax$0.30 / $1.20 per 1M tokens1M7Feb 2026
GLM 4.7Z.ai$0.60 / $2.20 per 1M tokens200K9Jan 2026
Kimi K2 ThinkingMoonshot AI$0.60 / $2.50 per 1M tokens256K9Nov 2025
GLM 4.6Z.ai$0.60 / $2.20 per 1M tokens200K7Oct 2025
DeepSeek V3.1DeepSeek$0.50 / $1.50 per 1M tokens160K12Aug 2025
GPT OSS 120BOpenAI$0.10 / $0.50 per 1M tokens128K22Aug 2025
Kimi K2 InstructMoonshot AI$0.60 / $2.50 per 1M tokens128K6Jul 2025
DeepSeek V3DeepSeek$0.77 / $0.77 per 1M tokens64K15Jan 2025