Mistral AI releases document-understanding OCR API Mistral OCR
Mistral OCR
Mistral AI released Mistral OCR, an optical character recognition API that takes images and PDFs and outputs interleaved text and images in order. It handles complex layouts such as tables, formulas and LaTeX.
Why it matters: Mistral gives benchmark comparisons, multilingual performance and pricing for Mistral OCR, showing how usable document parsing is in a RAG pipeline.