OCRRouter

docTR vs Nougat

Pick docTR if you need word-level text with coordinates from invoices, receipts or other business documents, and you want an Apache-2.0 library you can use commercially. Pick Nougat if you convert English scientific papers with heavy math into Markdown and LaTeX, and your use is non-commercial. The main split is output and licence: docTR returns words and boxes under Apache-2.0, Nougat returns Markdown with LaTeX under CC-BY-NC weights.

docTRmindee/doctrNougatmeta/nougat
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed0.9 s / page3.0 s / page
Best forWord-level OCR with positionsarXiv-style papers
InputsPDF, imagesPDF, images
LanguagesMainly Latin scriptsMainly English
Max pages per request500200
TablesNo✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxes✓ YesNo
Confidence✓ YesNo
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 docTR if

  • Its Apache-2.0 licence has no commercial restriction, so you can ship it in a product.
  • It returns a nested page, block, line and word structure with coordinates as JSON, which suits custom extraction on invoices and receipts.
  • You can choose detection and recognition architectures, use straight or rotated boxes, and train your own models in Python.

Choose Nougat if

  • It is built for academic papers, trained on arXiv and PubMed Central documents.
  • It outputs LaTeX for equations and tables inside Mathpix-compatible .mmd Markdown, which docTR does not produce at all.
  • It offers small and base checkpoints with a simple CLI and API for converting math-heavy PDFs.

Key differences

docTRNougat
LicenceApache-2.0Code MIT; weights CC-BY-NC, so no commercial use
Output formatsJSON, plain text, bounding boxesMarkdown, LaTeX
Tables and formulasNo table, formula or Markdown output; words and lines onlyLaTeX for equations and tables in .mmd Markdown
Best document typeInvoices and receipts feeding custom extraction, word-level OCREnglish arXiv-style scientific papers
LanguagesNot publishedWorks best on English; Chinese, Russian and Japanese do not work
Known failureSplit-crop merging misjoins readings across repeated characters (issue #2229); cropping images gives poorer results (issue #2007)Repetition loops on 1.5% of test pages in the paper, more on out-of-domain documents; repetition detection can drop pages as MISSING_PAGE (issue #11)
Hardware and priceCPU or NVIDIA GPU; GPU Docker images need CUDA 12.2 or newer; free, self-hostedFree for non-commercial use, self-hosted; benchmarks Not published

Sources

What each one is

docTR

Open-source OCR library from Mindee with separate text detection and recognition models.

docTR 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": "mindee/doctr","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

docTR alternativesNougat alternativesBest OCR models in 2026