OCRRouter

Nougat vs GOT-OCR 2.0

Pick Nougat for English arXiv-style papers where you need math and tables as LaTeX in Mathpix-style Markdown, and only for non-commercial work. Pick GOT-OCR 2.0 when you need formulas, sheet music, chemical structures or region-specific OCR, or when the Nougat weights licence blocks you. Watch for GOT-OCR 2.0's looping and false text on blank pages, and Nougat's repetition loops on out-of-domain documents.

Nougatmeta/nougatGOT-OCR 2.0stepfun/got-ocr-2
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed3.0 s / page1.5 s / page
Best forarXiv-style papersFormatted text, formulas and charts
InputsPDF, imagesimages
LanguagesMainly EnglishChinese, English
Max pages per request200100
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxesNo✓ Yes
ConfidenceNoNo
FormsNoNo
MultilingualNoNo
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 Nougat if

  • It is built for academic papers and trained on arXiv and PubMed Central documents.
  • It outputs LaTeX for equations and tables in Mathpix-compatible .mmd Markdown.
  • It ships small and base checkpoints with a simple CLI and API.

Choose GOT-OCR 2.0 if

  • It reads text, formulas, tables, charts, sheet music and geometry in one 580M-parameter model.
  • It can run region OCR guided by box coordinates or color.
  • It supports dynamic resolution and multi-page OCR, and is merged into Hugging Face Transformers with batched inference.

Key differences

NougatGOT-OCR 2.0
LicenceCode MIT; weights CC-BY-NC, so no commercial useCode Apache-2.0; training data CC BY-NC 4.0
How you run itSelf-hosted Python package with CLI and APISelf-hosted; available in Hugging Face Transformers; CUDA 11.8 and PyTorch 2.0.1 per README, CPU users pointed to a llama.cpp port
PriceFree for non-commercial use; you pay for computeFree; you pay for compute
Output formatsMarkdown, LaTeXPlain text, Markdown, LaTeX, TikZ, SMILES, kern
LanguagesWorks best on English; Chinese, Russian and Japanese do not workGood for English and Chinese documents
Benchmark scoresNot publishedNot published
Known failureRepetition loops on 1.5% of test pages, more on out-of-domain documents; repetition detection can drop pages as MISSING_PAGEOutput can start looping characters midway; wrong text on images with no text; format mode gives much worse results than plain OCR mode

Sources

What each one is

Nougat

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

Nougat details

GOT-OCR 2.0

Unified OCR model that reads plain text, tables, formulas, sheet music and charts.

GOT-OCR 2.0 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": "meta/nougat","fallbacks": ["stepfun/got-ocr-2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Nougat alternativesGOT-OCR 2.0 alternativesBest OCR models in 2026