We Use Cookies

    We use cookies to enhance your browsing experience, analyze site traffic, and personalize content. By clicking "Accept All", you consent to our use of cookies. You can customize your preferences or reject non-essential cookies.

    Learn more about our cookie policy
    Feature Spotlight · Mistral OCR 4

    Mistral OCR 4 is live on AI·Collab

    The world's best document extraction engine just got a major upgrade — now with bounding boxes, typed-block classification, inline confidence scores and 170-language coverage. Sharper document AI on AI·Collab, still at 4 credits per page.

    Basics
    ≈ 9 min read
    Document AI
    v4 upgrade

    What we shipped

    Around 90% of the world's organizational knowledge lives in documents — PDFs, scans, handwritten notes, complex technical papers. Mistral OCR is the engine that turns those documents into AI-ready knowledge on AI·Collab, and it just moved to its most capable version yet: Mistral OCR 4. Where earlier generations focused on converting a page into clean text and tables, OCR 4 returns a structured representation of the whole document. Every block is localized with a bounding box, classified by type, and given inline confidence scores — so downstream systems know not just what the document says, but where each element sits, what role it plays, and how confident the model is.

    On AI·Collab, OCR 4 powers document upload and the RAG pipeline behind the scenes. You keep the same simple workflow — upload a PDF, ask questions with any of 300+ models — but retrieval is sharper because the extracted content is cleaner, better structured, and citation-ready. And the price for you is unchanged: 4 credits per page.

    What's new in OCR 4

    OCR 4 is a small, focused model that goes well beyond plain text extraction. Independent annotators preferred it over every leading OCR and document-AI system Mistral tested, with win rates averaging 72%. Here are the headline changes.

    Bounding boxes

    Mistral's most-requested capability: every extracted block is localized with a bounding box, so text can be highlighted in context and mapped back to its exact position on the page — the foundation for reliable, auditable data pipelines.

    Typed-block classification

    OCR 4 classifies each block by type — titles, tables, equations, signatures and more — turning a flat page into clean, labelled units that make better retrieval chunks for RAG and structured connectors.

    Inline confidence scores

    Per-page and per-word confidence scores travel with the output, enabling source-grounded citations, redactions and human-in-the-loop verification where it matters — legal, financial and compliance work.

    170 languages

    Support for 170 languages across 10 language groups, with measurable gains on specialized and low-resource scripts where many competing systems degrade sharply.

    Same price for you: 4 credits per page

    Mistral OCR 4 raises the bar on quality, but your cost on AI·Collab does not change. Document processing stays at a flat, transparent 4 credits per page — no surprise upgrade fee, no separate tier.

    Per PDF page4 credits
    Per 1,000 pages≈ €3.64 / 1,000 pages

    Credits never expire and can be used across all AI·Collab features. Usage is tracked transparently in your dashboard, so you always know exactly what you're paying for. Hard limits per document remain 1,000 pages and 50 MB.

    Comprehensive document understanding

    OCR 4 handles the vast majority of document types found in organizations and everyday settings — and it keeps everything that made previous versions excellent.

    Complex document elements

    Understands interleaved imagery, mathematical expressions, tables and advanced layouts such as LaTeX formatting — perfect for scientific papers with charts, graphs, equations and figures.

    Advanced table reconstruction

    Reconstructs table structures with headers, merged cells, multi-row blocks and column hierarchies, preserving layout so tables stay queryable rather than collapsing into unreadable text.

    Handwriting recognition

    Accurately interprets cursive, mixed-content annotations and handwritten text layered over printed forms — ideal for digitizing historical documents, forms and personal notes.

    Mathematical expressions

    Processes complex formulas and equations reliably, emitting clean LaTeX — perfect for scientific papers, technical documentation and educational materials.

    Broad format & compression support

    Accepts PDF, DOC, PPT and OpenDocument, and handles JBIG2-compressed PDFs — a common scanned format that causes crashes and extraction failures in many other systems.

    How it benchmarks

    Mistral evaluated OCR 4 against leading AI-native OCR models, frontier general-purpose models, enterprise document services and its own OCR 3 — in blind human preference tests and on public benchmarks.

    72%
    Human win rate vs. competitors
    85.20
    OlmOCRBench (public)
    93.07
    OmniDocBench
    0.98
    Crawl Multilingual (internal)
    170
    Languages supported
    600+
    Documents in human eval

    Mistral notes that public OCR benchmarks have known scoring limitations (ground-truth errors, equivalent LaTeX marked as mismatches, multi-column reading order), which more often penalize correct output than reward incorrect output — so treat aggregate scores as directional and evaluate on your own documents.

    Benchmarks, methodology and screenshots: Mistral — Introducing OCR 4 (official announcement)

    What the upgrade unlocks

    The move from clean text to structured, classified, confidence-scored output changes what you can build on top of your documents in AI·Collab.

    Sharper RAG answers

    Clean, typed blocks make better retrieval units, so hybrid search finds the right passages more often — and answers cite the right part of the right page. It's the ingestion layer behind AI·Collab's RAG pipeline.

    Agentic document workflows

    Structural primitives (blocks, boxes, types) let agents move from reading documents to acting on them — form filling, invoice processing and compliance checks — especially in legal, financial services and healthcare.

    Verifiable & compliant pipelines

    Confidence scores and bounding boxes support redactions, source-grounded citations and human-in-the-loop verification, so regulated teams can trust and audit what the model extracted.

    Enterprise search & knowledge bases

    Turn archives, technical literature, invoices and filings into indexed, answer-ready knowledge — then query it across documents with any of 300+ models on AI·Collab.

    How to use it on AI·Collab

    Nothing changes in your workflow — OCR 4 is already the engine behind document upload and the knowledge base. Here's the flow.

    1

    Upload your document

    Upload a PDF or image in the chat, or add it to a knowledge base. OCR 4 automatically detects and processes the document — text, images, tables and structure.

    2

    Automatic processing

    Processing typically completes in seconds, even for complex multi-page documents. The extracted, structured content is added to your knowledge base, ready for search.

    3

    Choose your retrieval mode

    Click the file title to open document details. Keep Using Focused Retrieval on (default) for cost-effective segmented retrieval, or turn it off to load the entire document for maximum context.

    4

    Ask with any model

    Query your document with any of 300+ AI models via hybrid RAG search — including EU-hosted, ZDR-labeled options for GDPR-sensitive work.

    Cost consideration

    Using Entire Document gives the most complete context but consumes far more tokens (and credits) than focused retrieval — for example, a 1,000-page document might use 288K+ tokens in full-context mode versus 3–5K with focused retrieval. Choose the mode that fits your task and budget.

    FAQ

    Do I need to do anything to use Mistral OCR 4?

    No. OCR 4 is already the engine behind document upload and the knowledge base on AI·Collab. Just upload a PDF or image as usual — you automatically get the upgraded extraction quality.

    Does OCR 4 cost more than the previous version?

    No. Document processing on AI·Collab stays at a flat 4 credits per page (≈ €3.64 per 1,000 pages), regardless of the underlying model version. Credits never expire and are tracked transparently in your dashboard.

    What's actually new in version 4?

    OCR 4 adds bounding boxes, typed-block classification (titles, tables, equations, signatures and more) and inline per-page and per-word confidence scores, plus expanded coverage to 170 languages across 10 language groups. In Mistral's blind human evaluation it was preferred over every competing system tested, with win rates averaging 72%.

    How does OCR 4 improve my results on AI·Collab?

    Cleaner, structured, classified output makes better retrieval chunks, so the RAG pipeline surfaces the right passages more reliably and answers cite the right part of the right page. It's especially noticeable on complex documents — tables, equations, multi-column layouts and multilingual content.

    What are the document limits?

    Up to 1,000 pages and 50 MB per document. Multiple documents can be added to the same knowledge base for cross-document search — for example two 800-page books become 1,600 pages searchable together.

    Is my document data kept private?

    Documents are processed for extraction and stored in your knowledge base for retrieval. You can query them with EU-hosted, ZDR-labeled models for GDPR-sensitive work — see the model catalog for the current ZDR/EU-hosting status per model.

    Benchmark figures and capability descriptions are from Mistral's published OCR 4 announcement (mistral.ai/news/ocr-4) and reflect the state at publish time. Pricing reflects the AI·Collab model catalog. Credit rates, limits and model labels can change — the model catalog and your account dashboard are always the authoritative source for live prices and availability.

    Related Articles

    Ready to Experience 300+ AI Models?

    Get started today. Access models from OpenAI, Google, Anthropic, Grok and more.

    GDPR compliant · Zero data retention · Cancel anytime