OCRRouter

dots.ocr vs Pixtral

Pick dots.ocr for new document parsing work: it is built for PDFs to Markdown with layout, tables as HTML and formulas as LaTeX, and it is MIT-licensed. Pick Pixtral only if you already run on the Mistral API or need question answering over charts and documents, because Mistral marks it deprecated and no longer maintained.

dots.ocrrednote/dots-ocrPixtralmistral/pixtral
TypeOpen sourceVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.5 s / page3.0 s / page
Best forMultilingual document parsingQuestions about document images
InputsPDF, imagesimages
Languages100+ languagesMultilingual
Max pages per request500500
Tables✓ YesNo
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ YesNo
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 dots.ocr if

  • It returns layout boxes, categories and text in one pass, with tables as HTML and formulas as LaTeX.
  • It is a 3B model with MIT-licensed code, and the original scores 79.1 on olmOCR-bench (83.9 for the dots.mocr 1.5 release).
  • It targets multilingual PDFs with mixed tables and text, and the dots.mocr-svg variant converts charts and diagrams to SVG.

Choose Pixtral if

  • It suits question answering over charts and documents, with 90.7 ANLS on DocVQA and 81.8 on ChartQA per Mistral.
  • It is available through the Mistral API at a launch price of $0.15 per million input and output tokens, so existing Mistral integrations keep working.
  • It has Apache-2.0 open weights and a 128K token context, which allows many images per request.

Key differences

dots.ocrPixtral
PurposeDocument parsing model that outputs layout, text, tables and formulasGeneral vision language model with OCR as one of its abilities
LicenceMIT (the repository also includes a separate dots.ocr license agreement file)Apache-2.0
How you run itSelf-host only, with vLLM or Hugging Face Transformers; single CUDA GPU is the documented pathMistral API (pixtral-12b-2409) or self-hosted open weights
PriceFree to self-host, you pay for compute$0.15 per million input and output tokens at API launch; free to self-host
Size3B parameters (1.7B LLM backbone)12.4B parameters (12B decoder + 400M vision encoder)
Output formatsJSON, Markdown, HTML, LaTeX, bounding boxes, SVGPlain text, Markdown, JSON
Known failureRuns of ellipses or underscores can make output repeat endlessly; tables above 1000 grid cells raised an error and dropped the page in a Docling issueReported accuracy drop on handwriting, small fonts and non-Latin scripts; Q4 quantization reported to degrade small text OCR; deprecated by Mistral

Sources

What each one is

dots.ocr

Single vision model from rednote that does layout detection and content recognition together.

dots.ocr details

Pixtral

Mistral's open-weight vision models, Pixtral 12B and Pixtral Large. Mistral's API no longer serves them, so they run self-hosted.

Pixtral 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": "rednote/dots-ocr","fallbacks": ["mistral/pixtral"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

dots.ocr alternativesPixtral alternativesBest OCR models in 2026