LiteLLMModels

Weights & Biases model pricing

As of October 10, 2026, 28 Weights & Biases models are available through LiteLLM. The most recently added are DeepSeek V4.1 Flash, Granite 4.2 8B, GLM 5.3 Flash. Prices below are Weights & Biases's list prices.

How to call Weights & Biases with LiteLLM

Weights & Biases models

ModelLabPriceContextProvidersAdded
DeepSeek V4.1 FlashDeepSeek$0.20 / $0.65 per 1M tokens1M8Sep 2026
Granite 4.2 8B–$0.10 / $0.15 per 1M tokens131K1Sep 2026
GLM 5.3 FlashZ.ai$0.15 / $0.50 per 1M tokens1M11Aug 2026
Granite 4.1 8B–$0.05 / $0.10 per 1M tokens131K1Aug 2026
Mellum2 12B A2.5b Instruct–$0.05 / $0.10 per 1M tokens131K1Aug 2026
Nvidia Nemotron 3 Ultra 550B A55BNVIDIA$0.50 / $2.15 per 1M tokens262K3Aug 2026
Nvidia Nemotron 3.5 Lightning 30B A3BNVIDIA$0.07 / $0.20 per 1M tokens262K1Aug 2026
Qwen3 14B InstructAlibaba$0.05 / $0.22 per 1M tokens33K1Aug 2026
Qwen3.8 27BAlibaba$0.40 / $3 per 1M tokens262K5Aug 2026
DeepSeek V4 FlashDeepSeek$0.13 / $0.28 per 1M tokens262K22Jun 2026
DeepSeek V4 ProDeepSeek$1.15 / $2.55 per 1M tokens1M17Jun 2026
Gemma 4 26B A4B ITGoogle$0.10 / $0.30 per 1M tokens262K8Jun 2026
Gemma 4 31B ITGoogle$0.10 / $0.34 per 1M tokens262K11Jun 2026
GLM 5.2Z.ai$0.76 / $2.42 per 1M tokens1M19Jun 2026
Kimi K2.7 CodeMoonshot AI$0.71 / $3.50 per 1M tokens262K14Jun 2026
MiniMax M3MiniMax$0.23 / $0.96 per 1M tokens262K9Jun 2026
Qwen3.6 27BAlibaba$0.60 / $3.60 per 1M tokens262K6Jun 2026
Qwen3.6 35B A3BAlibaba$0.25 / $1.25 per 1M tokens262K8Jun 2026
Kimi K2.6Moonshot AI$0.65 / $3.41 per 1M tokens262K13Apr 2026
Qwen3.5 35B A3BAlibaba$0.25 / $1.25 per 1M tokens262K3Mar 2026
Kimi K2.5Moonshot AI$0.60 / $3 per 1M tokens256K8Feb 2026
Qwen3 30B A3B Instruct 2507Alibaba$0.10 / $0.30 per 1M tokens262K3Dec 2025
DeepSeek V3.1DeepSeek$0.55 / $1.65 per 1M tokens161K12Aug 2025
GPT OSS 120BOpenAI$0.03 / $0.17 per 1M tokens131K22Aug 2025
GPT OSS 20BOpenAI$0.03 / $0.13 per 1M tokens131K14Aug 2025
Llama 3.3 70B InstructMeta$0.71 / $0.71 per 1M tokens128K18Dec 2024
Llama 3.1 70B InstructMeta$0.80 / $0.80 per 1M tokens131K11Jul 2024
Llama 3.1 8B InstructMeta$0.22 / $0.22 per 1M tokens131K13Jul 2024