Mistral Document AI

Drive the product through a documented public API G

Agent access

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

Connect an agent via an official MCP server G

Agent access

Plug MCP servers into this product so it can use their tools G

Agent access

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

Point an agent at llms.txt or agent-oriented docs G

Agent access

Run the product headlessly / in CI for automation G

Agent access

Operate the product with natural-language commands G

Agentic features

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

Explore an interactive API reference with runnable examples G

Api quality

Rely on versioned APIs with a documented deprecation policy G

Api quality

Use an official CLI G

Agent access

Build against official SDKs G

Agent access

Issue scoped/least-privilege API credentials for an agent G

Agent access

Set up automations that run autonomously in the background G

Agentic features

Subscribe to events via webhooks G

Agent access

Test against a sandbox environment without touching production data G

Api quality

I supply a JSON schema and get back validated structured fields extracted from the document C

Schemas

Scanned and photographed documents OCR accurately — skewed pages, stamps, low quality scans included C

Ocr

The API parses complex real-world PDFs — multi-column layouts, headers, footers, footnotes — into clean, correctly ordered content C

Layout

Complex tables — merged cells, nested headers, multi-page spans — come out as faithful HTML/markdown structure C

Tables

Output comes pre-chunked for RAG — semantic boundaries, metadata, embedding-ready segments — not a wall of text C

Chunking

Export all of my data in open formats and leave G

Self-host the core product G

Long parses run as async jobs with status polling and completion webhooks, so my pipeline never blocks C

Async

Prevent my data from being used to train AI models G

Uploaded documents get zero-retention handling with SOC 2 and HIPAA options, so I can process contracts and medical records C

Compliance

Define rules that trigger actions automatically on events G

Official typed SDKs for Python and TypeScript cover the full API — parse, extract, jobs — with sensible defaults C

Sdks

I get clean markdown/JSON designed for LLM consumption, with noise like repeated headers and page furniture stripped C

Output

Parsed output preserves document hierarchy — headings, sections, reading order — so downstream LLMs see structure, not soup C

Layout

Every extracted field carries provenance — page number, bounding box, source snippet — so agents can cite and humans can verify C

Grounding

One API handles my whole document mix — PDF, DOCX, PPTX, XLSX, HTML, images, email — without per-format plumbing C

Formats

Figures and charts are extracted or described (VLM summaries, image crops) with positions traceable back to the source page C

Figures

I turn extracted tables into typed rows/JSON I can load into a database without manual cleanup C

Tables

Extractions carry calibrated confidence scores with a human-in-the-loop review path for low-confidence fields C

Review

Non-English documents — including CJK and right-to-left scripts — parse with the same fidelity as English C

Languages

Perform bulk operations across many items at once G

Thousand-page documents and multi-gigabyte files process reliably without timeouts or silent truncation C

Scale limits

Choose where my data is stored (region/residency) G

Run the extraction stack in my own VPC or fully self-hosted when documents can't leave my infrastructure C

Deployment

A fast synchronous mode returns results in seconds for interactive apps, with latency documented per mode C

Latency

Control data retention and deletion G

I push high-volume batches — millions of pages — with documented rate limits and predictable throughput G

Scale

Opt out of telemetry and usage tracking G

Do everything through the API that I can do in the UI G

Multi-document packets are classified and split automatically — one upload, per-document results C

Splitting

Read the product's source under an open license G

Schedule recurring jobs or workflows G

Handwritten fields and annotations are recognized and extracted, flagged with confidence when uncertain C

Ocr

I drag a document into a web playground and see parse/extract results before writing any code C

Playground

The vendor publishes reproducible accuracy benchmarks and I can run my own evals before committing C

Evals

Version, review, and roll back my automations G