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.
Weights & Biases models
| Model | Lab | Price | Context | Providers | Added |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | DeepSeek | $0.20 / $0.65 per 1M tokens | 1M | 8 | Sep 2026 |
| Granite 4.2 8B | – | $0.10 / $0.15 per 1M tokens | 131K | 1 | Sep 2026 |
| GLM 5.3 Flash | Z.ai | $0.15 / $0.50 per 1M tokens | 1M | 11 | Aug 2026 |
| Granite 4.1 8B | – | $0.05 / $0.10 per 1M tokens | 131K | 1 | Aug 2026 |
| Mellum2 12B A2.5b Instruct | – | $0.05 / $0.10 per 1M tokens | 131K | 1 | Aug 2026 |
| Nvidia Nemotron 3 Ultra 550B A55B | NVIDIA | $0.50 / $2.15 per 1M tokens | 262K | 3 | Aug 2026 |
| Nvidia Nemotron 3.5 Lightning 30B A3B | NVIDIA | $0.07 / $0.20 per 1M tokens | 262K | 1 | Aug 2026 |
| Qwen3 14B Instruct | Alibaba | $0.05 / $0.22 per 1M tokens | 33K | 1 | Aug 2026 |
| Qwen3.8 27B | Alibaba | $0.40 / $3 per 1M tokens | 262K | 5 | Aug 2026 |
| DeepSeek V4 Flash | DeepSeek | $0.13 / $0.28 per 1M tokens | 262K | 22 | Jun 2026 |
| DeepSeek V4 Pro | DeepSeek | $1.15 / $2.55 per 1M tokens | 1M | 17 | Jun 2026 |
| Gemma 4 26B A4B IT | $0.10 / $0.30 per 1M tokens | 262K | 8 | Jun 2026 | |
| Gemma 4 31B IT | $0.10 / $0.34 per 1M tokens | 262K | 11 | Jun 2026 | |
| GLM 5.2 | Z.ai | $0.76 / $2.42 per 1M tokens | 1M | 19 | Jun 2026 |
| Kimi K2.7 Code | Moonshot AI | $0.71 / $3.50 per 1M tokens | 262K | 14 | Jun 2026 |
| MiniMax M3 | MiniMax | $0.23 / $0.96 per 1M tokens | 262K | 9 | Jun 2026 |
| Qwen3.6 27B | Alibaba | $0.60 / $3.60 per 1M tokens | 262K | 6 | Jun 2026 |
| Qwen3.6 35B A3B | Alibaba | $0.25 / $1.25 per 1M tokens | 262K | 8 | Jun 2026 |
| Kimi K2.6 | Moonshot AI | $0.65 / $3.41 per 1M tokens | 262K | 13 | Apr 2026 |
| Qwen3.5 35B A3B | Alibaba | $0.25 / $1.25 per 1M tokens | 262K | 3 | Mar 2026 |
| Kimi K2.5 | Moonshot AI | $0.60 / $3 per 1M tokens | 256K | 8 | Feb 2026 |
| Qwen3 30B A3B Instruct 2507 | Alibaba | $0.10 / $0.30 per 1M tokens | 262K | 3 | Dec 2025 |
| DeepSeek V3.1 | DeepSeek | $0.55 / $1.65 per 1M tokens | 161K | 12 | Aug 2025 |
| GPT OSS 120B | OpenAI | $0.03 / $0.17 per 1M tokens | 131K | 22 | Aug 2025 |
| GPT OSS 20B | OpenAI | $0.03 / $0.13 per 1M tokens | 131K | 14 | Aug 2025 |
| Llama 3.3 70B Instruct | Meta | $0.71 / $0.71 per 1M tokens | 128K | 18 | Dec 2024 |
| Llama 3.1 70B Instruct | Meta | $0.80 / $0.80 per 1M tokens | 131K | 11 | Jul 2024 |
| Llama 3.1 8B Instruct | Meta | $0.22 / $0.22 per 1M tokens | 131K | 13 | Jul 2024 |
