Wandb LLM API pricing
Every model Wandb serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.
Models served
28
on this provider
Cheapest input
$0.03
per 1M tokens
Cheapest output
$0.10
per 1M tokens
Max context
1M
tokens
| Model ID | |||||
|---|---|---|---|---|---|
| gpt-oss-120b | OpenAI | 131K | $0.03 | $0.17 | wandb/openai/gpt-oss-120b |
| gpt-oss-20b | OpenAI | 131K | $0.03 | $0.13 | wandb/openai/gpt-oss-20b |
| Granite 4.1 8B | IBM | 131K | $0.05 | $0.10 | wandb/ibm-granite/granite-4.1-8b |
| Mellum2 12B A2 5B Instruct | Other | 131K | $0.05 | $0.10 | wandb/JetBrains/Mellum2-12B-A2.5B-Instruct |
| Qwen3 14B Instruct | Alibaba | 33K | $0.05 | $0.22 | wandb/OpenPipe/Qwen3-14B-Instruct |
| Gemma 4 31B | 262K | $0.10 | $0.34 | wandb/google/gemma-4-31B-it | |
| Nvidia Nemotron 3.5 Lightning 30B A3b | NVIDIA | 262K | $0.10 | $0.25 | wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B |
| Qwen3 30B A3B Instruct 2507 | Alibaba | 262K | $0.10 | $0.30 | wandb/Qwen/Qwen3-30B-A3B-Instruct-2507 |
| DeepSeek V4 Flash 0731 | DeepSeek | 1M | $0.13 | $0.28 | wandb/deepseek-ai/DeepSeek-V4-Flash-0731 |
| DeepSeek V4 Flash 0423 | DeepSeek | 1M | $0.14 | $0.28 | wandb/deepseek-ai/DeepSeek-V4-Flash |
| Llama 3.1 8B Instruct | Meta | 200K | $0.22 | $0.22 | wandb/meta-llama/Llama-3.1-8B-Instruct |
| MiniMax M3 | MiniMax | 1M | $0.23 | $0.96 | wandb/MiniMaxAI/MiniMax-M3 |
| Qwen3.6 35B A3B | Alibaba | 262K | $0.25 | $1.25 | wandb/Qwen/Qwen3.6-35B-A3B |
| Qwen3.5-35B-A3B | Alibaba | 262K | $0.25 | $1.25 | wandb/Qwen/Qwen3.5-35B-A3B |
| MiniMax M2.5 | MiniMax | 1M | $0.30 | $1.20 | wandb/MiniMaxAI/MiniMax-M2.5 |
| Qwen3.8 27B | Alibaba | 262K | $0.40 | $3.00 | wandb/Qwen/Qwen3.8-27B |
| DeepSeek V3 1 | DeepSeek | 164K | $0.55 | $1.65 | wandb/deepseek-ai/DeepSeek-V3.1 |
| Kimi K2.5 | Moonshot | 262K | $0.60 | $3.00 | wandb/moonshotai/Kimi-K2.5 |
| Kimi K2 Instruct | Moonshot | 131K | $0.60 | $2.50 | wandb/moonshotai/Kimi-K2-Instruct |
| Qwen3.6 27B | Alibaba | 262K | $0.60 | $3.60 | wandb/Qwen/Qwen3.6-27B |
| Kimi K2.6 | Moonshot | 262K | $0.65 | $3.41 | wandb/moonshotai/Kimi-K2.6 |
| Llama 3.3 70B Instruct | Meta | 131K | $0.71 | $0.71 | wandb/meta-llama/Llama-3.3-70B-Instruct |
| Kimi K2.7 Code | Moonshot | 262K | $0.71 | $3.50 | wandb/moonshotai/Kimi-K2.7-Code |
| Nvidia Nemotron 3 Ultra 550B A55b | NVIDIA | 262K | $0.75 | $2.75 | wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B |
| GLM 5.2 | Zhipu | 1M | $0.76 | $2.42 | wandb/zai-org/GLM-5.2 |
| Llama 3.1 70B Instruct | Meta | 131K | $0.80 | $0.80 | wandb/meta-llama/Llama-3.1-70B-Instruct |
| Qwen3 Coder 480B A35b Instruct | Alibaba | 262K | $1.00 | $1.50 | wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct |
| DeepSeek V4 Pro 0423 | DeepSeek | 1M | $1.15 | $2.55 | wandb/deepseek-ai/DeepSeek-V4-Pro |
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI