LLM token prices: llamagate
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 |
|---|---|---|---|---|---|---|---|
| codellama-7b | codellama-7b | USD 0.06 | USD 0.12 | – | 16,384 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-coder-6.7b | deepseek-coder-6.7b | USD 0.06 | USD 0.12 | – | 16,384 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-r1-7b-qwen | deepseek-r1-7b-qwen | USD 0.08 | USD 0.15 | – | 131,072 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-r1-8b | deepseek-r1-8b | USD 0.10 | USD 0.20 | – | 65,536 | 2026-10-23 22:53 UTC | source cross-check |
| dolphin3-8b | dolphin3-8b | USD 0.08 | USD 0.15 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| gemma3-4b | gemma3-4b | USD 0.03 | USD 0.08 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| llama-3.1-8b | llama-3.1-8b | USD 0.03 | USD 0.05 | – | 131,072 | 2026-10-23 22:53 UTC | source cross-check |
| llama-3.2-3b | llama-3.2-3b | USD 0.04 | USD 0.08 | – | 131,072 | 2026-10-23 22:53 UTC | source cross-check |
| llava-7b | llava-7b | USD 0.10 | USD 0.20 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| mistral-7b-v0.3 | mistral-7b-v0.3 | USD 0.10 | USD 0.15 | – | 32,768 | 2026-10-23 22:53 UTC | source cross-check |
| nomic-embed-text | nomic-embed-text | USD 0.02 | Free | – | 8,192 | 2026-10-23 22:53 UTC | source cross-check |
| openthinker-7b | openthinker-7b | USD 0.08 | USD 0.15 | – | 32,768 | 2026-10-23 22:53 UTC | source cross-check |
| qwen2.5-coder-7b | qwen2.5-coder-7b | USD 0.06 | USD 0.12 | – | 32,768 | 2026-10-23 22:53 UTC | source cross-check |
| qwen3-8b | qwen3-8b | USD 0.04 | USD 0.14 | – | 32,768 | 2026-10-23 22:53 UTC | source cross-check |
| qwen3-embedding-8b | qwen3-embedding-8b | USD 0.02 | Free | – | 40,960 | 2026-10-23 22:53 UTC | source cross-check |
| qwen3-vl-8b | qwen3-vl-8b | USD 0.15 | USD 0.55 | – | 32,768 | 2026-10-23 22:53 UTC | source cross-check |