NewsAgency

Introducing OCR 4

3 dakika okuma süresi

Introducing OCR 4

June 23, 2026

Today, we’re releasing Mistral OCR 4, featuring bounding boxes, block classification, and inline confidence scores alongside extracted text. The model supports 170 languages across 10 language groups, runs in a single container for fully self-hosted deployments, and serves as an ingestion component for enterprise search, RAG, and domain-specific retrieval pipelines.

Highlights

Breakthrough performance. Independent annotators prefer OCR 4 over every leading OCR and document-AI system tested, with win rates averaging 72%, alongside the top overall score on OlmOCRBench (85.20).

Segmentation, not just text. Alongside the extracted text, OCR 4 returns bounding boxes, typed-block classification (titles, tables, equations, signatures, and more), and inline confidence scores. Bounding boxes localize text for in-context highlighting and reliable data pipelines.

Integrated with Mistral Search Toolkit (public preview). OCR 4 is an ingestion component of Search Toolkit, Mistral’s open-source, composable search framework, announced at the AI Now Summit.

Multilingual coverage. Support for 170 languages across 10 language groups, with measurable gains on specialized and low-resource languages where several competing systems degrade.

Run on your own infrastructure. OCR 4 is compact enough to deploy on a single container, keeping document data in your environment for residency, sovereignty, and compliance, while supporting cost-efficient, high-throughput batch processing.

Overview

Mistral OCR 4 extracts and structures content from a wide range of documents. Where previous generations focused on converting a page into clean text and tables, OCR 4 returns a structured representation of the document. Each block is localized with a bounding box, classified by type, and inline confidence scores are generated per-page and per-word.

OCR 4 accepts common enterprise formats, including PDF, DOC, PPT, and OpenDocument, and supports 170 languages across 10 language groups. Developers integrate the model via API, and teams can use Document AI in Mistral Studio for an application-level, no-code path.

Mistral OCR 4 through the API is priced at 2 per 1,000 pages. Document AI is priced at $5 per 1,000 pages.

Benchmarks

Annotators preferred OCR 4 in the majority of documents across all systems tested. OCR 4 achieves the top overall score amongst the models tested on the public OlmOCRBench (85.20) and leads Mistral’s internal Crawl Multilingual evaluation (.98). On OmniDocBench, OCR 4 achieves a score of 93.07.

  • Document parsing and extraction: complex, multilingual documents.
  • Retrieval-Augmented Generation (RAG): structured, classified, citation-ready content for semantic chunking.
  • Agentic workflows: form filling, invoice processing, and compliance checks.
  • Structured data pipelines using confidence scores for human-in-the-loop verification.
  • Enterprise search and knowledge bases: OCR as a data-source component for custom ingestion.

Availability

Both Mistral OCRv4 and Document AI (powered by OCRv4) are available via API through Mistral Studio, Amazon SageMaker, Microsoft Foundry, and coming soon Snowflake Parse Document. For organizations with stringent data-privacy requirements, OCR 4 also offers a self-hosting option.

“The availability of Mistral Document AI with OCR 4 in Microsoft Foundry marks an important milestone in our partnership,” said Kimmi Grewal, VP, AI Ecosystem Partnerships, Microsoft.

A production webinar with demos and Q&A is scheduled for July 7, 2026.

Grafik Görünümü