LLM token prices: replicate
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 |
|---|---|---|---|---|---|---|---|
| anthropic/claude-3.5-haiku | anthropic/claude-3.5-haiku | USD 1.00 | USD 5.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| anthropic/claude-3.5-sonnet | anthropic/claude-3.5-sonnet | USD 3.75 | USD 18.75 | – | 2026-10-23 22:53 UTC | source cross-check | |
| anthropic/claude-3.7-sonnet | anthropic/claude-3.7-sonnet | USD 3.00 | USD 15.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| anthropic/claude-4-sonnet | anthropic/claude-4-sonnet | USD 3.00 | USD 15.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| anthropic/claude-4.5-haiku | anthropic/claude-4.5-haiku | USD 1.00 | USD 5.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| anthropic/claude-4.5-sonnet | anthropic/claude-4.5-sonnet | USD 3.00 | USD 15.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| deepseek-ai/deepseek-r1 | deepseek-ai/deepseek-r1 | USD 3.75 | USD 10.00 | – | 65,536 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-ai/deepseek-v3 | deepseek-ai/deepseek-v3 | USD 1.45 | USD 1.45 | – | 65,536 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-ai/deepseek-v3.1 | deepseek-ai/deepseek-v3.1 | USD 0.672 | USD 2.016 | – | 163,840 | 2026-10-23 22:53 UTC | source cross-check |
| google/gemini-2.5-flash | google/gemini-2.5-flash | USD 0.30 | USD 2.50 | – | 2026-10-23 22:53 UTC | source cross-check | |
| google/gemini-3-pro | google/gemini-3-pro | USD 2.00 | USD 12.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| ibm-granite/granite-3.3-8b-instruct | ibm-granite/granite-3.3-8b-instruct | USD 0.03 | USD 0.25 | – | 2026-10-23 22:53 UTC | source cross-check | |
| meta/llama-2-13b | meta/llama-2-13b | USD 0.10 | USD 0.50 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| meta/llama-2-13b-chat | meta/llama-2-13b-chat | USD 0.10 | USD 0.50 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| meta/llama-2-70b | meta/llama-2-70b | USD 0.65 | USD 2.75 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| meta/llama-2-70b-chat | meta/llama-2-70b-chat | USD 0.65 | USD 2.75 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| meta/llama-2-7b | meta/llama-2-7b | USD 0.05 | USD 0.25 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| meta/llama-2-7b-chat | meta/llama-2-7b-chat | USD 0.05 | USD 0.25 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| meta/llama-3-70b | meta/llama-3-70b | USD 0.65 | USD 2.75 | – | 8,192 | 2026-10-23 22:53 UTC | source cross-check |
| meta/llama-3-70b-instruct | meta/llama-3-70b-instruct | USD 0.65 | USD 2.75 | – | 8,192 | 2026-10-23 22:53 UTC | source cross-check |
| meta/llama-3-8b | meta/llama-3-8b | USD 0.05 | USD 0.25 | – | 8,086 | 2026-10-23 22:53 UTC | source cross-check |
| meta/llama-3-8b-instruct | meta/llama-3-8b-instruct | USD 0.05 | USD 0.25 | – | 8,086 | 2026-10-23 22:53 UTC | source cross-check |
| mistralai/mistral-7b-instruct-v0.2 | mistralai/mistral-7b-instruct-v0.2 | USD 0.05 | USD 0.25 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| mistralai/mistral-7b-v0.1 | mistralai/mistral-7b-v0.1 | USD 0.05 | USD 0.25 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| mistralai/mixtral-8x7b-instruct-v0.1 | mistralai/mixtral-8x7b-instruct-v0.1 | USD 0.30 | USD 1.00 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| openai/gpt-4.1 | openai/gpt-4.1 | USD 2.00 | USD 8.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/gpt-4.1-mini | openai/gpt-4.1-mini | USD 0.40 | USD 1.60 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/gpt-4.1-nano | openai/gpt-4.1-nano | USD 0.10 | USD 0.40 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/gpt-4o | openai/gpt-4o | USD 2.50 | USD 10.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/gpt-4o-mini | openai/gpt-4o-mini | USD 0.15 | USD 0.60 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/gpt-5 | openai/gpt-5 | USD 1.25 | USD 10.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/gpt-5-mini | openai/gpt-5-mini | USD 0.25 | USD 2.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/gpt-5-nano | openai/gpt-5-nano | USD 0.05 | USD 0.40 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/gpt-oss-120b | openai/gpt-oss-120b | USD 0.18 | USD 0.72 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/gpt-oss-20b | openai/gpt-oss-20b | USD 0.09 | USD 0.36 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/o1 | openai/o1 | USD 15.00 | USD 60.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/o1-mini | openai/o1-mini | USD 1.10 | USD 4.40 | – | 2026-10-23 22:53 UTC | source cross-check | |
| openai/o4-mini | openai/o4-mini | USD 1.00 | USD 4.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| qwen/qwen3-235b-a22b-instruct-2507 | qwen/qwen3-235b-a22b-instruct-2507 | USD 0.264 | USD 1.06 | – | 2026-10-23 22:53 UTC | source cross-check | |
| xai/grok-4 | xai/grok-4 | USD 7.20 | USD 36.00 | – | 2026-10-23 22:53 UTC | source cross-check |