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

Property Description
Model ID mistral-ocr-2505
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
Quota limits
  • us-central1:
    • QPM: 30
    • Pages per request: 1,000 (1 page = 1 million input tokens and 1 million output tokens)
    • Context length: 1,000 pages
  • europe-west4:
    • QPM: 30
    • Pages per request: 1,000 (1 page = 1 million input tokens and 1 million output tokens)
    • Context length: 1,000 pages
Pricing See Pricing.