Mistral OCR (25.05)

Mistral OCR (25.05) is an Optical Character Recognition API for document understanding. The model comprehends each element of documents such as media, text, tables, and equations.

View model card in Model Garden

Model ID mistral-ocr-2505
Launch stage GA
Supported inputs & outputs
  • Inputs:
    Documents
  • Outputs:
    Text
Usage types
Versions
  • Mistral OCR (25.05)
    • Launch stage: GA
    • Release date: May 14, 2025
Supported regions

Model availability
  • United States
    • us-central1
  • Europe
    • europe-west4

ML processing
  • United States
    • Multi-region
  • Europe
    • Multi-region
Quota limits

us-central1:

  • QPM: 30
  • Pages per request: 30 (1 page = 1 million input tokens and 1 million output tokens)
  • Context length: 30 pages
  • Max request size: 30MB for streaming, 10MB for unary

europe-west4:

  • QPM: 30
  • Pages per request: 30 (1 page = 1 million input tokens and 1 million output tokens)
  • Context length: 30 pages
  • Max request size: 30MB for streaming, 10MB for unary
Pricing See Pricing.