Mistral OCR vs Unstructured
Pick Mistral OCR for high-volume PDF to Markdown for RAG and batch scans of business documents, mainly because of the low price: $2 per 1,000 pages, or $1 through the Batch API. Pick Unstructured when you ingest mixed file types (PDF, HTML, Word, PowerPoint, email, images) or need to self-host. Use the hosted Unstructured platform rather than the open-source library if tables matter, since the vendor's own benchmark shows 0.426 for OSS versus 0.866 hosted.
Mistral OCRmistral/mistral-ocr | Unstructuredunstructured/unstructured | |
|---|---|---|
| Type | OCR API | OCR API |
| Price | 25 credits / page | 20 credits / page |
| Per 1,000 pages | $25.00 | $20.00 |
| Typical speed | 0.9 s / page | 3.0 s / page |
| Best for | High-volume PDF to Markdown | Mixed file types into RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 100+ languages | Multilingual |
| Max pages per request | 1,000 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
Which to choose
Choose Mistral OCR if
- It costs $2 per 1,000 pages, and the Batch API halves OCR to $1 per 1,000 pages.
- OCR 3 reconstructs tables as HTML with rowspan and colspan.
- Mistral reports a 74% win rate for OCR 3 over OCR 2 on forms, scans, tables and handwriting.
Choose Unstructured if
- One library handles PDFs, HTML, Word, PowerPoint, emails and images.
- The Apache-2.0 open-source library is free, can be self-hosted, and has many connectors.
- The first 10,000 hosted pages are free, and the strategies Auto, Fast, High-Res and VLM let you trade speed for quality.
Key differences
| Mistral OCR | Unstructured | |
|---|---|---|
| How you run it | Hosted API only | Self-hosted open-source library or hosted API |
| Licence | Proprietary | Apache-2.0 library; proprietary hosted platform |
| Price | $2 per 1,000 pages; $3 with structured annotations; $1 per 1,000 via Batch API | Hosted: first 10,000 pages free, then $0.015 per page (about $15 per 1,000); open-source library is free |
| Output formats | Markdown, HTML, JSON, images | JSON, HTML, plain text, bounding boxes |
| Input scope | Document OCR for PDFs and scans, returned as Markdown with tables and extracted images | PDFs, HTML, Word, PowerPoint, emails and images partitioned into typed elements |
| Benchmark | OmniDocBench v1.6 overall 85.66; the first version scored 78.83 on v1.5 (independent) | Table cell content 0.426 (OSS) vs 0.866 (hosted), reported by the authors |
| Known failure | Hallucinated text on unreadable handwriting; colored-background pages returned as images with no OCR text (2025 release); changed checkbox states and misread characters on a dense financial table page | hi_res tables cut off at edges and drop first letters; table OCR ignores language settings; the library sends usage telemetry by default |
Sources
- Mistral OCR 3 announcement
- VentureBeat on OCR 3 pricing
- OmniDocBench v1.6 leaderboard
- Reducto test of Mistral OCR
- Unstructured pricing
- Unstructured GitHub README
What each one is
Mistral OCR
Fast document OCR that returns clean Markdown with tables and embedded images.
Mistral OCR detailsUnstructured
Document ETL for RAG. Partitions many file types into typed elements; open-source library too.
Unstructured detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "mistral/mistral-ocr","fallbacks": ["unstructured/unstructured"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Mistral OCR alternativesUnstructured alternativesBest OCR models in 2026