OCRRouter

Docling vs Nougat

Pick Docling for general document ingestion: PDFs, Office files, HTML and images into structured JSON, under an MIT licence that allows commercial use. Pick Nougat only for English scientific papers where you need LaTeX math and tables, and only for non-commercial work, because its weights are CC-BY-NC.

Doclingibm/doclingNougatmeta/nougat
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.2 s / page3.0 s / page
Best forStructured export for RAGarXiv-style papers
InputsPDF, images, DOCXPDF, images
LanguagesLatin scripts, CJKMainly English
Max pages per request500200
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ YesNo
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 Docling if

  • You need one API for PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails and XBRL.
  • You are building a commercial product, since the code is MIT (individual models carry their own licences).
  • You want lossless JSON that keeps layout, reading order and table structure, or you use LangChain or LlamaIndex.

Choose Nougat if

  • Your inputs are English arXiv-style papers and you need equations and tables as LaTeX in Mathpix-compatible Markdown.
  • Your work is non-commercial, so the CC-BY-NC weights are acceptable.
  • You want a small or base checkpoint with a simple CLI and API, trained on arXiv and PubMed Central documents.

Key differences

DoclingNougat
LicenceMIT (individual models have their own licences)Code MIT; weights CC-BY-NC, so no commercial use
Input formatsPDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails, XBRLScientific PDF pages
Output formatsMarkdown, HTML, JSON, DocTags, plain textMarkdown (.mmd) and LaTeX
How OCR worksPluggable engines (EasyOCR, Tesseract, RapidOCR) and VLMs such as the 258M GraniteDocling; scan accuracy depends on the engine you plug inSingle Visual Transformer model, trained on arXiv and PubMed Central
LanguagesNot publishedBest on English; README says Chinese, Russian and Japanese do not work
PricingFree, self-hosted (you pay for compute)Free for non-commercial use, self-hosted (you pay for compute)
Known failureTesseract full-page OCR in 2.143.1 drops words and numbers (issue #5254); reading order can merge neighbouring columns (issue #5132)Repetition loops on 1.5% of test pages in the paper, more on out-of-domain documents; looping pages can be dropped as MISSING_PAGE (issue #11)

Sources

What each one is

Docling

IBM's open-source document converter with a structured document model.

Docling 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": "ibm/docling","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Docling alternativesNougat alternativesBest OCR models in 2026