LLM token prices: wandb
LLM API prices per 1M tokens: input, output and cached input, from each provider's listing or the LiteLLM cross-check.
Sources for this list
- Last verified 2026-10-23T22:53:51+00:00 · https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json (community cross-check,
litellm)
No first-party source is read for this model yet; this value is a community cross-check and can lag the provider.
| SKU | Name | Input / 1M | Output / 1M | Cached input | Context window | Last verified | Source |
|---|---|---|---|---|---|---|---|
| JetBrains/Mellum2-12B-A2.5B-Instruct | JetBrains/Mellum2-12B-A2.5B-Instruct | USD 0.05 | USD 0.10 | – | 131,000 | 2026-10-23 22:53 UTC | source cross-check |
| MiniMaxAI/MiniMax-M3 | MiniMaxAI/MiniMax-M3 | USD 0.23 | USD 0.96 | USD 0.05 | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| OpenPipe/Qwen3-14B-Instruct | OpenPipe/Qwen3-14B-Instruct | USD 0.05 | USD 0.22 | – | 32,800 | 2026-10-23 22:53 UTC | source cross-check |
| Qwen/Qwen3-30B-A3B-Instruct-2507 | Qwen/Qwen3-30B-A3B-Instruct-2507 | USD 0.10 | USD 0.30 | – | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| Qwen/Qwen3.5-35B-A3B | Qwen/Qwen3.5-35B-A3B | USD 0.25 | USD 1.25 | – | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| Qwen/Qwen3.6-27B | Qwen/Qwen3.6-27B | USD 0.60 | USD 3.60 | USD 0.12 | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| Qwen/Qwen3.6-35B-A3B | Qwen/Qwen3.6-35B-A3B | USD 0.25 | USD 1.25 | – | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| Qwen/Qwen3.8-27B | Qwen/Qwen3.8-27B | USD 0.40 | USD 3.00 | USD 0.15 | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-ai/DeepSeek-V3.1 | deepseek-ai/DeepSeek-V3.1 | USD 0.55 | USD 1.65 | – | 161,000 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-ai/DeepSeek-V4-Flash | deepseek-ai/DeepSeek-V4-Flash | USD 0.14 | USD 0.28 | USD 0.07 | 1,049,000 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-ai/DeepSeek-V4-Flash-0731 | deepseek-ai/DeepSeek-V4-Flash-0731 | USD 0.13 | USD 0.28 | USD 0.07 | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-ai/DeepSeek-V4-Pro | deepseek-ai/DeepSeek-V4-Pro | USD 1.15 | USD 2.55 | USD 0.20 | 1,049,000 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-ai/DeepSeek-V4-Pro-0813 | deepseek-ai/DeepSeek-V4-Pro-0813 | USD 1.31 | USD 3.96 | USD 0.044 | 1,049,000 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-ai/DeepSeek-V4.1-Flash | deepseek-ai/DeepSeek-V4.1-Flash | USD 0.20 | USD 0.65 | USD 0.03 | 1,049,000 | 2026-10-23 22:53 UTC | source cross-check |
| google/gemma-4-26B-A4B-it | google/gemma-4-26B-A4B-it | USD 0.10 | USD 0.30 | USD 0.05 | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| google/gemma-4-31B-it | google/gemma-4-31B-it | USD 0.10 | USD 0.34 | – | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| ibm-granite/granite-4.1-8b | ibm-granite/granite-4.1-8b | USD 0.05 | USD 0.10 | – | 131,000 | 2026-10-23 22:53 UTC | source cross-check |
| ibm-granite/granite-4.2-8b | ibm-granite/granite-4.2-8b | USD 0.10 | USD 0.15 | USD 0.05 | 131,000 | 2026-10-23 22:53 UTC | source cross-check |
| meta-llama/Llama-3.1-70B-Instruct | meta-llama/Llama-3.1-70B-Instruct | USD 0.80 | USD 0.80 | – | 131,000 | 2026-10-23 22:53 UTC | source cross-check |
| meta-llama/Llama-3.1-8B-Instruct | meta-llama/Llama-3.1-8B-Instruct | USD 0.22 | USD 0.22 | – | 131,000 | 2026-10-23 22:53 UTC | source cross-check |
| meta-llama/Llama-3.3-70B-Instruct | meta-llama/Llama-3.3-70B-Instruct | USD 0.71 | USD 0.71 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| moonshotai/Kimi-K2.5 | moonshotai/Kimi-K2.5 | USD 0.60 | USD 3.00 | USD 0.10 | 262,144 | 2026-10-23 22:53 UTC | source cross-check |
| moonshotai/Kimi-K2.6 | moonshotai/Kimi-K2.6 | USD 0.65 | USD 3.41 | USD 0.15 | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| moonshotai/Kimi-K2.7-Code | moonshotai/Kimi-K2.7-Code | USD 0.71 | USD 3.50 | USD 0.15 | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | USD 0.50 | USD 2.15 | USD 0.10 | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B | nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B | USD 0.07 | USD 0.20 | USD 0.04 | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B | nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B | USD 0.15 | USD 0.75 | USD 0.02 | 1,049,000 | 2026-10-23 22:53 UTC | source cross-check |
| openai/gpt-oss-120b | openai/gpt-oss-120b | USD 0.03 | USD 0.17 | – | 131,000 | 2026-10-23 22:53 UTC | source cross-check |
| openai/gpt-oss-20b | openai/gpt-oss-20b | USD 0.03 | USD 0.13 | – | 131,000 | 2026-10-23 22:53 UTC | source cross-check |
| reflection/Beam-1.0-501B-A23B | reflection/Beam-1.0-501B-A23B | USD 1.00 | USD 3.00 | USD 0.10 | 1,049,000 | 2026-10-23 22:53 UTC | source cross-check |
| zai-org/GLM-5.2 | zai-org/GLM-5.2 | USD 0.76 | USD 2.42 | USD 0.14 | 1,049,000 | 2026-10-23 22:53 UTC | source cross-check |
| zai-org/GLM-5.3 | zai-org/GLM-5.3 | USD 1.20 | USD 4.00 | USD 0.19 | 1,049,000 | 2026-10-23 22:53 UTC | source cross-check |
| zai-org/GLM-5.3-Flash | zai-org/GLM-5.3-Flash | USD 0.15 | USD 0.50 | USD 0.05 | 1,049,000 | 2026-10-23 22:53 UTC | source cross-check |