Mistral AI
Mistral AI
Vision model · France ·Dec 2025

OCR 3

Vision Proprietary

About OCR 3

OCR 3 is an AI model developed by Mistral AI, in the vision category, released in 2025, made available as a proprietary (API-only) model. OCR service powering Document AI stack (version v25.12)..

On this page you'll find OCR 3's full specifications. Review provider pricing and benchmark scores below, or compare OCR 3 head-to-head with other vision models.

Links

Community

Would you run OCR 3 again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like OCR 3

Frequently asked questions

What is OCR 3?

OCR service powering Document AI stack (version v25.12). It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created OCR 3?

OCR 3 was developed by Mistral AI and released in 2025.

Is OCR 3 open source or proprietary?

OCR 3 is a proprietary model. It is accessed through an API rather than by downloading the weights.

How much does OCR 3 cost?

Pricing for OCR 3 depends on the provider. See the providers table on this page for the latest API rates.

How does OCR 3 perform on benchmarks?

Benchmark scores for OCR 3 are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

Mistral OCR 3: AI That Can Actually Read Documents

Know a great video about OCR 3?