Directory

AI model API pricing

Every current, legacy and deprecated text and multimodal model we track across 11 providers, with input, output and cached token rates in USD per 1M tokens. Prices checked 2026-07-02.

  • Codestral

    Mistral AI

    • Context
    • Input$0.30 / 1M tokens
    • Output$0.90 / 1M tokens
    • Cached
  • Devstral 2

    Mistral AI

    • Context
    • Input$0.40 / 1M tokens
    • Output$2.00 / 1M tokens
    • Cached
    • Context
    • Input$0.10 / 1M tokens
    • Output$0.30 / 1M tokens
    • Cached
  • Leanstral

    Mistral AI

    • Context
    • Input$0.00 / 1M tokens
    • Output$0.00 / 1M tokens
    • Cached
    • Context
    • Input$2.00 / 1M tokens
    • Output$5.00 / 1M tokens
    • Cached
  • Magistral Small

    Mistral AI

    • Context
    • Input$0.50 / 1M tokens
    • Output$1.50 / 1M tokens
    • Cached
    • Context
    • Input$0.20 / 1M tokens
    • Output$0.20 / 1M tokens
    • Cached
    • Context
    • Input$0.10 / 1M tokens
    • Output$0.10 / 1M tokens
    • Cached
    • Context
    • Input$0.15 / 1M tokens
    • Output$0.15 / 1M tokens
    • Cached
  • Mistral Large 3

    Mistral AI

    • Context
    • Input$0.50 / 1M tokens
    • Output$1.50 / 1M tokens
    • Cached
    • Context
    • Input$1.50 / 1M tokens
    • Output$7.50 / 1M tokens
    • Cached
    • Context
    • Input$0.10 / 1M tokens
    • Output
    • Cached
  • Mistral OCR 4

    Mistral AI

    • Context
    • Input
    • Output
    • Cached
  • Mistral Small 4

    Mistral AI

    • Context
    • Input$0.15 / 1M tokens
    • Output$0.60 / 1M tokens
    • Cached
  • Mistral NeMo

    Mistral AI

    Legacy
    • Context
    • Input$0.15 / 1M tokens
    • Output$0.15 / 1M tokens
    • Cached
  • Mixtral 8x22B

    Mistral AI

    Legacy
    • Context
    • Input$2.00 / 1M tokens
    • Output$6.00 / 1M tokens
    • Cached
  • Mixtral 8x7B

    Mistral AI

    Legacy
    • Context
    • Input$0.70 / 1M tokens
    • Output$0.70 / 1M tokens
    • Cached

Embedding models

Priced per input token only — there is no output leg for embeddings.

  • Codestral Embed

    Mistral AI

    • Context
    • Input$0.15 / 1M tokens
    • Output
    • Cached
  • Mistral Embed

    Mistral AI

    • Context
    • Input$0.10 / 1M tokens
    • Output
    • Cached
Image & audio models (4)

Usually billed per image, per second or with separate speech/text rates rather than per token — see each model’s page for its documented unit price.