OCRRouter

Unlimited OCR vs Nougat

Pick Unlimited OCR for long multi-page documents, bulk PDF to text for RAG, and anything you ship commercially, because it is MIT licensed and parses 40+ pages in one pass. Pick Nougat only for English arXiv-style papers where you need LaTeX math and tables, and only for non-commercial use, because its weights are CC-BY-NC.

Unlimited OCRbaidu/unlimited-ocrNougatmeta/nougat
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.2 s / page3.0 s / page
Best forBooks and very long documentsarXiv-style papers
InputsPDF, imagesPDF, images
Languages30+ languagesMainly English
Max pages per request1,000200
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
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 Unlimited OCR if

  • The MIT licence allows commercial use with no copyleft, while Nougat's weights are CC-BY-NC.
  • It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go through in one request.
  • It returns block types and bounding boxes with the text, which helps layout-aware extraction.

Choose Nougat if

  • It is trained on arXiv and PubMed Central papers, so it fits English scientific papers.
  • It outputs LaTeX for equations and tables in Mathpix-compatible .mmd Markdown, which suits math-heavy PDFs.
  • It ships small and base checkpoints with a simple CLI and API.

Key differences

Unlimited OCRNougat
LicenceMITCode MIT; weights CC-BY-NC
Commercial useAllowedNot allowed with the weights
How you run itSelf-host with vLLM, SGLang or transformers; also hosted in Baidu Cloud's OCR productSelf-hosted Python package only
Output formatsMarkdown, plain text, bounding boxesMarkdown (.mmd) and LaTeX
Best document typeLong reports and books, bulk PDF to text for RAGEnglish arXiv-style scientific papers with heavy math
HardwareNVIDIA GPU with CUDA 12.9 or 13.0; version 2 runs out of memory on 12 GB GPUs under SGLangNot published
Known failureRepetition and looping on some pages (issue #55), hallucinated text (issue #58), formatting mostly lostRepetition loops on 1.5% of test pages, more on out-of-domain documents; pages can be dropped as MISSING_PAGE (issue #11); Chinese, Russian and Japanese do not work

Sources

What each one is

Unlimited OCR

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

Unlimited OCR details

Nougat

Meta's model that converts academic PDFs to Markdown with LaTeX math.

Nougat 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": "baidu/unlimited-ocr","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Unlimited OCR alternativesNougat alternativesBest OCR models in 2026