← Model explorer

Sourced model profile · Current through July 14, 2026

Mistral OCR

A closed-weight Mistral API model documented for OCR, chat, and language generation across vision, language, and multimodal domains.

Developed byMistral
Released
March 6, 2025

What the evidence says

These facts come from the reviewed Epoch AI catalog artifact and its linked primary record. They describe the model. They do not rank it.

Developer [1]
Mistral
Released [1]
March 6, 2025
Domains [1]
Multimodal · Vision · Language
Tasks [1]
Character recognition (OCR) · Chat · Language generation
Access [1]
API access
Weights [1]
Closed

Where it may fit

These are evidence-bounded screening suggestions, not performance claims or purchase recommendations.

Document OCR evaluation

Consider it for hosted evaluations where character recognition is the explicit task.

Evidence fields: tasks, access [1]

OCR-to-language workflows

Consider it for prototypes that connect visual or multimodal input to chat or language generation.

Evidence fields: domains, tasks [1]

Limitations

The source record does not report supported document formats, languages, accuracy, page limits, price, latency, or safety evaluations. It does not support an OCR quality ranking.

Current standing

According to the LMArena snapshot published July 12, 2026, no exact match for this catalog record appears in the style-controlled text category, so this page reports no current rating for Mistral OCR.

Head-to-head comparisons

Source-backed pair pages that put Mistral OCR next to another documented model. None declares a winner beyond what a named source's numbers say.