Mistral OCR vs Unlimited OCR
Pick Mistral OCR if you want a hosted API with a published per-page price and no GPU to run, mainly for batches of scanned business documents. Pick Unlimited OCR if you need an MIT-licensed model you can self-host, or long reports and books parsed in one request with bounding boxes. The main split is how you run it: a metered API versus a 3B model on your own NVIDIA hardware.
Mistral OCRmistral/mistral-ocr | Unlimited OCRbaidu/unlimited-ocr | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 25 credits / page | 2 credits / page |
| Per 1,000 pages | $25.00 | $2.00 |
| Typical speed | 0.9 s / page | 1.2 s / page |
| Best for | High-volume PDF to Markdown | Books and very long documents |
| Inputs | PDF, images | PDF, images |
| Languages | 100+ languages | 30+ languages |
| Max pages per request | 1,000 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| 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 is a hosted API at $2 per 1,000 pages, or $1 per 1,000 pages through the Batch API, so there is no hardware to manage.
- OCR 3 rebuilds tables as HTML with rowspan and colspan, which helps on forms, scans and tables.
- It fits high-volume PDF to Markdown for RAG and batches of scanned business documents.
Choose Unlimited OCR if
- The MIT licence allows commercial use with no copyleft, and the model is free to self-host (you pay for compute).
- It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go in one request.
- It returns block types and bounding boxes next to the text, which suits layout-aware extraction.
Key differences
| Mistral OCR | Unlimited OCR | |
|---|---|---|
| Licence | Proprietary | MIT |
| How you run it | Hosted API only (current version mistral-ocr-2512, OCR 3) | Self-host with vLLM, SGLang or transformers, or use the hosted endpoint in Baidu Cloud's OCR product |
| Price | $2 per 1,000 pages; $3 with structured annotations; $1 per 1,000 via Batch API | Free to self-host, you pay for compute; Baidu Cloud hosted price not published |
| Output formats | Markdown, HTML, JSON, images | Markdown, plain text, bounding boxes |
| Hardware | None needed, runs on Mistral's servers | NVIDIA GPU with CUDA 12.9 or 13.0; Unlimited OCR 2 under SGLang runs out of memory on 12 GB GPUs; no CPU-only use |
| Long documents | Not published | 40+ pages in one pass; context capped at 32,768 tokens, and multi-page input only works in base mode |
| Known failures | 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 | Text repetition and looping (issue #55); hallucinated text (issue #58); bold and italic formatting mostly lost (text formatting score 0.97 on ParseBench) |
Sources
- Mistral OCR 3 announcement
- VentureBeat on OCR 3 pricing
- Reducto test of Mistral OCR
- Hugging Face model card
- GitHub repo
- Issue #116 OOM on 12 GB
What each one is
Mistral OCR
Fast document OCR that returns clean Markdown with tables and embedded images.
Mistral OCR detailsUnlimited OCR
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Unlimited OCR 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": ["baidu/unlimited-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Mistral OCR alternativesUnlimited OCR alternativesBest OCR models in 2026