Wispr Flow - Don’t type, just speak
Mini toolsMistral OCR 4
By Mistral AI
Model family: Mistral
Mistral OCR 4 converts documents into structured representations, going beyond plain text extraction. Each block is localized with a bounding box, classified by type (titles, tables, equations, signatures, and more), and assigned inline confidence scores per page and per word. Accepts PDF, DOC, PPT, and OpenDocument formats. Supports 170 languages across 10 language groups, with measurable gains on low-resource languages. Priced at $4 per 1,000 pages via API, with a 50% Batch API discount. Document AI mode extends the same endpoint to return structured JSON matching a user-defined schema and can annotate detected images via a vision-language model call. Suited for RAG pipelines, agentic workflows (form filling, invoice processing, compliance checks), semantic chunking, and enterprise search. Available via Mistral Studio, Amazon SageMaker, and Microsoft Foundry. Self-hosting in a single container is available for enterprise customers with data-sovereignty requirements.
New
Multimodal
Gen 3
Overview
Mistral OCR 4 extracts and structures content from PDF, DOC, PPT, and OpenDocument files, returning text alongside bounding boxes, typed block classification (titles, tables, equations, signatures), and inline confidence scores. Supports 170 languages across 10 language groups. Deployable via API or self-hosted in a single container for data-sovereignty compliance.
About Mistral AI
Mistral AI is a company that specializes in artificial intelligence and machine learning solutions.
View Company Profile
Last updated: June 24, 2026
