OCRRouter

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-ocrUnlimited OCRbaidu/unlimited-ocr
TypeOCR APIOpen source
Price25 credits / page2 credits / page
Per 1,000 pages$25.00$2.00
Typical speed0.9 s / page1.2 s / page
Best forHigh-volume PDF to MarkdownBooks and very long documents
InputsPDF, imagesPDF, images
Languages100+ languages30+ languages
Max pages per request1,0001,000
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

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 OCRUnlimited OCR
LicenceProprietaryMIT
How you run itHosted 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 APIFree to self-host, you pay for compute; Baidu Cloud hosted price not published
Output formatsMarkdown, HTML, JSON, imagesMarkdown, plain text, bounding boxes
HardwareNone needed, runs on Mistral's serversNVIDIA 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 documentsNot published40+ pages in one pass; context capped at 32,768 tokens, and multi-page input only works in base mode
Known failuresHallucinated 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 tableText repetition and looping (issue #55); hallucinated text (issue #58); bold and italic formatting mostly lost (text formatting score 0.97 on ParseBench)

Sources

What each one is

Mistral OCR

Fast document OCR that returns clean Markdown with tables and embedded images.

Mistral OCR details

Unlimited OCR

Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.

Unlimited OCR details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

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