# Mistral OCR

DevFeed: [Mistral OCR](<https://devfeed.tech/articles/mistral-ocr-7073.md>)

Original publisher: [Read original article](<https://mistral.ai/news/mistral-ocr/>)

Published: 2025-03-06T17:00:00Z

Content type: release

Language: en

Sources: [Mistral AI Blog](<https://devfeed.tech/sources/mistral-ai-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [API](<https://devfeed.tech/topics/api.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [pdf](<https://devfeed.tech/topics/pdf.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [LaTeX](<https://devfeed.tech/topics/latex.md>), [Markdown](<https://devfeed.tech/topics/markdown.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [inference](<https://devfeed.tech/tags/inference.md>), [markdown](<https://devfeed.tech/tags/markdown.md>), [models](<https://devfeed.tech/tags/models.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [ocr](<https://devfeed.tech/tags/ocr.md>), [pdf](<https://devfeed.tech/tags/pdf.md>), [rag](<https://devfeed.tech/tags/rag.md>)

## AI overview

Mistral introduces Mistral OCR, an Optical Character Recognition API for understanding complex documents containing text, images, tables, equations, and advanced layouts. It accepts images and PDFs, produces ordered interleaved text and images, supports multilingual and multimodal documents, and is designed for use with RAG systems. The article also describes its availability, pricing, benchmarks, batch inference, structured output, and selective self-hosting.

## Source excerpt

The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.