Introducing Mistral OCR 3
Original: Research Introducing Mistral OCR 3 December 17, 2025 Mistral AI
Mistral OCR 3 improves document extraction across forms, scans, tables, and handwriting.
Mistral AI introduced Mistral OCR 3, a document extraction model focused on high-fidelity text, image, markdown, and HTML table output. The company says it achieves a 74% overall win rate over Mistral OCR 2 across forms, scanned documents, complex tables, and handwriting. It is available through API and the Document AI Playground in Mistral AI Studio, with pricing starting at $2 per 1,000 pages.
Mistral AI has released Mistral OCR 3, positioned as a next-generation document recognition and document understanding model. The focus is not simply turning images into text, but preserving the content and structure of documents so that downstream search, knowledge bases, agentic AI, or data processing pipelines can use them more easily. The company states that Mistral OCR 3 can extract text and embedded images from various documents, supports markdown output, and can reconstruct tables in HTML table form, including structural information such as headers, merged cells, multi-row blocks, and column hierarchies. This is especially important for teams that need to process reports, invoices, application forms, technical documents, or scientific reports, because downstream systems often need not just text but also an understanding of the relationships between fields and layout.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Mistral AI News →Related
Summaries are AI-generated; the original article is authoritative.