OCRRouter

TrOCR vs Nougat

Pick Nougat for English scientific papers where you need Markdown with LaTeX math and tables, as long as your product is non-commercial. Pick TrOCR for reading single text-line images, such as English handwriting or receipt lines, under an MIT licence. The main split is scope and licence: Nougat parses whole PDF pages but its weights are CC-BY-NC, while TrOCR reads one line at a time and needs a separate line detector.

TrOCRmicrosoft/trocrNougatmeta/nougat
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.2 s / page3.0 s / page
Best forHandwritten text linesarXiv-style papers
InputsimagesPDF, images
LanguagesEnglishMainly English
Max pages per request100200
TablesNo✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxesNoNo
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 TrOCR if

  • You need a commercial-friendly licence, since the TrOCR code is MIT licensed and Nougat's weights are CC-BY-NC.
  • You are reading English handwritten lines, and the large model reports a 2.89 character error rate on IAM.
  • You want to fine-tune a recognizer on your own line images, or use the separate checkpoints for handwritten (IAM), printed (SROIE) and scene text.

Choose Nougat if

  • You are converting English arXiv-style papers or math-heavy PDFs to Markdown with LaTeX equations and tables.
  • You need page-level output from a PDF, which TrOCR does not give you.
  • Your use is non-commercial and you want a simple CLI and API with small and base checkpoints.

Key differences

TrOCRNougat
Input unitSingle text-line images only; you need a separate line detectorScientific PDF pages
OutputPlain textMarkdown (Mathpix-style .mmd) with LaTeX for math and tables
LicenceMIT (microsoft/unilm repository)Code MIT; weights CC-BY-NC, so no commercial use
Price and hostingFree, self-hosted; you pay for computeFree for non-commercial use, self-hosted; you pay for compute
Model sizeBase 334M, large 558M parametersSmall and base checkpoints; parameter counts not published
LanguagesReleased checkpoints are English-focused; other languages need fine-tuningWorks best on English; Chinese, Russian and Japanese do not work
Known failureNo layout, table or page-level output; slow versus CRNN recognizers on CPURepetition loops on 1.5% of test pages, more on out-of-domain documents; looping pages can be dropped as MISSING_PAGE

Sources

What each one is

TrOCR

Transformer text recognition model. Reads single text lines, including handwriting.

TrOCR 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": "microsoft/trocr","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

TrOCR alternativesNougat alternativesBest OCR models in 2026