Back to models
Mistral AIactive

Mistral OCR 3

A proprietary Optical Character Recognition (OCR) model specialized in complex tables, forms, handwritten content, and multi-page PDFs, outputting high-fidelity Markdown or HTML structures.

Input / 1M tokens

N/A

Output / 1M tokens

N/A

Context window

N/A

Capabilities

  • Table Extraction
  • Handwriting Recognition
  • Layout Preservation
  • Multilingual Support
  • Markdown/HTML Output
  • Batch API