LLM token prices: ollama
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 2026-10-24T10:58:26+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 |
|---|---|---|---|---|---|---|---|
| codegeex4 | codegeex4 | Free | Free | – | 32,768 | 2026-10-24 10:58 UTC | source cross-check |
| codegemma | codegemma | Free | Free | – | 8,192 | 2026-10-24 10:58 UTC | source cross-check |
| codellama | codellama | Free | Free | – | 4,096 | 2026-10-24 10:58 UTC | source cross-check |
| deepseek-coder-v2-base | deepseek-coder-v2-base | Free | Free | – | 8,192 | 2026-10-24 10:58 UTC | source cross-check |
| deepseek-coder-v2-instruct | deepseek-coder-v2-instruct | Free | Free | – | 32,768 | 2026-10-24 10:58 UTC | source cross-check |
| deepseek-coder-v2-lite-base | deepseek-coder-v2-lite-base | Free | Free | – | 8,192 | 2026-10-24 10:58 UTC | source cross-check |
| deepseek-coder-v2-lite-instruct | deepseek-coder-v2-lite-instruct | Free | Free | – | 32,768 | 2026-10-24 10:58 UTC | source cross-check |
| deepseek-v3.1:671b-cloud | deepseek-v3.1:671b-cloud | Free | Free | – | 163,840 | 2026-10-24 10:58 UTC | source cross-check |
| gpt-oss:120b-cloud | gpt-oss:120b-cloud | Free | Free | – | 131,072 | 2026-10-24 10:58 UTC | source cross-check |
| gpt-oss:20b-cloud | gpt-oss:20b-cloud | Free | Free | – | 131,072 | 2026-10-24 10:58 UTC | source cross-check |
| internlm2_5-20b-chat | internlm2_5-20b-chat | Free | Free | – | 32,768 | 2026-10-24 10:58 UTC | source cross-check |
| llama2 | llama2 | Free | Free | – | 4,096 | 2026-10-24 10:58 UTC | source cross-check |
| llama2-uncensored | llama2-uncensored | Free | Free | – | 4,096 | 2026-10-24 10:58 UTC | source cross-check |
| llama2:13b | llama2:13b | Free | Free | – | 4,096 | 2026-10-24 10:58 UTC | source cross-check |
| llama2:70b | llama2:70b | Free | Free | – | 4,096 | 2026-10-24 10:58 UTC | source cross-check |
| llama2:7b | llama2:7b | Free | Free | – | 4,096 | 2026-10-24 10:58 UTC | source cross-check |
| llama3 | llama3 | Free | Free | – | 8,192 | 2026-10-24 10:58 UTC | source cross-check |
| llama3.1 | llama3.1 | Free | Free | – | 8,192 | 2026-10-24 10:58 UTC | source cross-check |
| llama3:70b | llama3:70b | Free | Free | – | 8,192 | 2026-10-24 10:58 UTC | source cross-check |
| llama3:8b | llama3:8b | Free | Free | – | 8,192 | 2026-10-24 10:58 UTC | source cross-check |
| mistral | mistral | Free | Free | – | 8,192 | 2026-10-24 10:58 UTC | source cross-check |
| mistral-7B-Instruct-v0.1 | mistral-7B-Instruct-v0.1 | Free | Free | – | 8,192 | 2026-10-24 10:58 UTC | source cross-check |
| mistral-7B-Instruct-v0.2 | mistral-7B-Instruct-v0.2 | Free | Free | – | 32,768 | 2026-10-24 10:58 UTC | source cross-check |
| mistral-large-instruct-2407 | mistral-large-instruct-2407 | Free | Free | – | 65,536 | 2026-10-24 10:58 UTC | source cross-check |
| mixtral-8x22B-Instruct-v0.1 | mixtral-8x22B-Instruct-v0.1 | Free | Free | – | 65,536 | 2026-10-24 10:58 UTC | source cross-check |
| mixtral-8x7B-Instruct-v0.1 | mixtral-8x7B-Instruct-v0.1 | Free | Free | – | 32,768 | 2026-10-24 10:58 UTC | source cross-check |
| orca-mini | orca-mini | Free | Free | – | 4,096 | 2026-10-24 10:58 UTC | source cross-check |
| qwen3-coder:480b-cloud | qwen3-coder:480b-cloud | Free | Free | – | 262,144 | 2026-10-24 10:58 UTC | source cross-check |
| vicuna | vicuna | Free | Free | – | 2,048 | 2026-10-24 10:58 UTC | source cross-check |