Mistral OCR 4
Layout-aware document OCR with bounding boxes, block typing, and inline confidence.
Document OCR product for layout-aware extraction of document content, producing bounding boxes, block classifications, and inline confidence scores across 170 languages; offered for API use and self-hosted deployments.
Recent stories
Chandra's developer said Mistral OCR 4 launch numbers for both Chandra and OCR 4 could not be reproduced with public code, and published scripts to show the gaps. The dispute matters because Mistral OCR 4 launched on leaderboard claims, and benchmark settings now directly affect model selection.
Mistral OCR 4 adds layout-aware extraction with bounding boxes, block typing, and inline confidence across 170 languages. Use it through the API or self-hosted deployments when document pipelines need structure, citations, redaction, and chunking.