Mistral OCR 4.1 Adds Paragraph-Level Bounding Boxes

Mistral OCR 4.1 Adds Paragraph-Level Bounding Boxes

Mistral AI has released OCR 4.1, the latest version of its OCR service powering the Document AI stack. The update introduces native paragraph-level bounding box extraction, structural block labels, and block-level confidence scores. Priced at €3.5 per 1,000 pages (or €4.38 per 1,000 annotated pages), it supports batching and structured annotations via the /v1/ocr endpoint. Available in public preview since July 16, 2026.

Our latest OCR service powering our Document AI stack, with native paragraph-level bounding box extraction, structural block labels, and block-level confidence scores.
  1. ComputerPerson

    I've got a scan from a book that I OCR with new releases. Ligatures, critical sigla, Fraktur letterforms, subscripts, superscripts, etc.

    Nothing special about this model for overly-detailed work like mine.

    It's been a while since I last tested (and discontinued my subscription), but the "pro" models from OpenAI dominate. Not surprising, given the price difference, but it would be nice if an OCR-specific model could perform better. It's worth mentioning that even the highest-end models do a pretty poor job with intricate text like mine.

  2. king_crimson

    At this point I lost all hope for Europe playing any significant role in the AI race. If that’s a good or a bad thing I don’t know, but it seems to me like that’s the reality.

  3. waldrews

    The VLM's are so good at complex document understanding now. But you just can't trust them not to invisibly censor sensitive clinical/legal docs, even at the maximally permissive settings.

    And the deep learning OCR-only models won't censor, but can and do hallucinate. I've yet to see a 'scan with different approaches and reconcile and say you're not sure if they don't agree' system just work for generic complex documents.

  4. merb

    1000 Pages / 3.5€ this is expensive as hell.

    If this is not fastly superior than something like tesseract it is not worth it.

  5. piterrro

    For anyone interested, I have an ocr pipeline running on rented GPUs, doing around 1000pages for 0.05-01 usd with around 0.8 seconds per page with full bounding boxes support for grounding.

    If you’re interested you can find contact to me via this profile.

    3.5 usd/1000 pages is just too expensive…

  6. ks2048

    Does anyone know a site that lets you browse examples of input / output pairs?, particularly with layout analysis (bounding boxes of figures, tables, etc).

  7. ianhawes

    I won't comment on accuracy, but in internal benchmarks, Mistral OCR is significantly faster than comparable APIs.

  8. maelito

    Given the latest vibe release's new "follow default" model option, we should see a new coding / general Mistral model, mistral 4, soon.

More from this day

2026-08-13