mistral-ocr-3-88968d4c·4 events·first seen Aliases: Mistral OCR 3, Mistral OCR 2, Mistral OCR, Mistral OCR 4
Mistral AI has released OCR 4, a new version of their optical character recognition model. The announcement was posted on Mistral's official news page and generated significant community interest on Hacker News with 398 points and 105 comments. OCR capabilities are increasingly relevant for document processing pipelines in AI applications.
Mistral AI released OCR 4, a document intelligence model supporting 170 languages across 10 language groups, with structured output including bounding boxes, typed-block classification, and inline confidence scores. The model claims top scores on OlmOCRBench (85.20) and wins 72% of head-to-head human preference evaluations against competing OCR and document-AI systems. It is deployable in a single container for self-hosted, data-sovereign environments and is priced at $4 per 1,000 pages via API. OCR 4 is integrated with Mistral's open-source Search Toolkit as an ingestion component for RAG and enterprise search pipelines.
Mistral AI has released Mistral OCR, an Optical Character Recognition API designed for deep document understanding, handling text, tables, equations, images, and complex layouts from PDFs and images. The model claims top benchmark scores across math, multilingual, scanned, and table categories, outperforming Google Document AI, Azure OCR, Gemini 1.5/2.0, and GPT-4o on an internal test set. It is priced at 1000 pages per dollar (with batch inference doubling that), available via la Plateforme API today, and is already deployed as the default document understanding model in Le Chat. A selective self-hosting option is offered for organizations with sensitive data requirements.
Mistral AI has released Mistral OCR 3 (model ID: mistral-ocr-2512), claiming a 74% overall win rate over its predecessor Mistral OCR 2 across forms, scanned documents, complex tables, and handwriting. The model supports markdown output with HTML-based table reconstruction and is priced at $2 per 1,000 pages ($1 with Batch API). It now powers the Document AI Playground in Mistral AI Studio, offering a drag-and-drop interface for parsing PDFs and images into text or structured JSON.