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.
- 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.
- 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.
- 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.
- 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.
- 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…
- 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).
- ianhawes
I won't comment on accuracy, but in internal benchmarks, Mistral OCR is significantly faster than comparable APIs.
- maelito
Given the latest vibe release's new "follow default" model option, we should see a new coding / general Mistral model, mistral 4, soon.