Mistral OCR

What Mistral OCR is

Mistral OCR is a service for understanding documents and extracting text. OCR 4.1 supplies paragraph-level bounding boxes, structural block labels and confidence scores for individual blocks. OCR 4 supports 170 languages across 10 language groups, plus table extraction, structure extraction and handwriting OCR. Teams can use the API, including batch processing, or the no-code Document AI interface in Mistral Studio. OCR 4 can run in a single container on an organization’s own infrastructure; self-managed deployment is available to enterprise customers. Mistral says self-hosting keeps document data within the customer’s environment. The service is also an ingestion component of Mistral Search Toolkit, an open-source framework for RAG and enterprise search. The listed API plan costs $4 per 1,000 pages per month, while Document AI costs $5 per 1,000 annotated pages. It is available through API, self-hosted and web options, with Python and TypeScript SDKs. Mistral says it is not intended for medical diagnosis, legal advice or judgment, high-stakes financial decisions, safety-critical systems, real-time processing or non-document inputs.