All models
Document AIStable
Mistral AIMistral OCR 4.1
Mistral's current Document AI OCR model for preserving reading order, tables, structure, locations, and confidence across multilingual files.
Plain-English overview
What Mistral OCR 4.1 actually is
Mistral OCR 4.1 turns PDFs, office documents, and images into structured machine-readable content. It can return Markdown, separate tables, paragraph-level bounding boxes, structural labels such as title or footer, and confidence at page, block, or word level.
The base OCR and structured-annotation prices are published separately, which helps teams distinguish simple document ingestion from schema-driven extraction. Online and batch workflows use the same Document AI stack.
Good fit for
- Layout-aware OCR for RAG
- Multilingual document archives
- Workflows that need boxes, labels, tables, or confidence
Category comparison
The facts that matter for documents models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Price per page
- $4 / 1K OCR pages · $5 / 1K annotatedA current provider rate and the exact page or annotation unit it covers.
- Accepted documents
- PDF, DOCX, PPTX, PNG, JPEG, AVIF and moreThe file and document types the listed endpoint is designed to process.
- What you get back
- Markdown, separate Markdown/HTML tables, structured annotationsMarkdown, tables, chunks, fields, descriptions, or another machine-readable result.
- Layout & confidence
- Paragraph boxes, block labels, page/block/word confidenceWhether the output preserves boxes, hierarchy, labels, reading order, or confidence information.
- Language coverage
- 40+ documentedProvider-documented language support without inferring unlisted languages.
- Where it runs
- Mistral OCR API and batch; verify regional endpoint supportDirect API, batch service, private environment, marketplace, or regional cloud route.
Pricing & comparisons
Estimate your cost
Set your usage. Your estimate updates as you type.
Counts pages, not files. A 10-page PDF counts as 10 pages. The estimate uses the document-processing rate available for each model.
Mistral OCR 4.1
Mistral AI
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
How this estimate works
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Where to get Mistral OCR 4.1
Availability
Regions and access stage
Generally available through Mistral's OCR API and Document AI workflow, with batch and structured-annotation support.
Optional EU and US regional endpoints are available only when the selected model and features are supported; verify OCR coverage before relying on residency.
Check live availabilityData and training
The route matters.
Mistral's commercial terms exclude model training by default except opt-in and preview exceptions. Standard API input and output retention is generally 30 rolling days unless zero data retention is enabled.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Mistral OCR 4.1 FAQ
What is Mistral OCR 4.1?
Mistral's current Document AI OCR model for preserving reading order, tables, structure, locations, and confidence across multilingual files. Mistral OCR 4.1 turns PDFs, office documents, and images into structured machine-readable content. It can return Markdown, separate tables, paragraph-level bounding boxes, structural labels such as title or footer, and confidence at page, block, or word level.
When was Mistral OCR 4.1 released?
Mistral OCR 4.1 was released on July 16, 2026 according to the cited provider materials.
Where can I access Mistral OCR 4.1?
Generally available through Mistral's OCR API and Document AI workflow, with batch and structured-annotation support. The access routes listed in this guide are Mistral AI.
How much does Mistral OCR 4.1 cost?
$4 / 1,000 pages · $5 annotated. Mistral lists $4 per 1,000 OCR pages and $5 per 1,000 annotated pages for structured extraction.
Where is Mistral OCR 4.1 available?
Generally available through Mistral's OCR API and Document AI workflow, with batch and structured-annotation support. Optional EU and US regional endpoints are available only when the selected model and features are supported; verify OCR coverage before relying on residency.
Is my Mistral OCR 4.1 API data used for training?
Mistral's commercial terms exclude model training by default except opt-in and preview exceptions. Standard API input and output retention is generally 30 rolling days unless zero data retention is enabled. The policy belongs to the provider route and account terms, so verify it again before production use.
Related comparisons
Head-to-head comparisons
Mistral OCR 4.1 vs Cohere Parse 5
Cohere's compact document parser for turning enterprise PDFs, presentations, and scans into retrieval-ready Markdown and layout metadata.
Open full comparisonMistral OCR 4.1 vs Google Gemini Layout Parser 1.6
Google Cloud's Gemini-assisted parser for preserving document hierarchy and creating context-rich chunks for enterprise search and RAG.
Open full comparisonMistral OCR 4.1 vs Google Document AI Custom Extractor 3.5
Google Cloud's Gemini-powered Document AI processor for extracting the exact fields and derived values defined in a business schema.
Open full comparison
