OCRRouter

OCRmyPDF vs Surya

Pick OCRmyPDF to make scanned PDF archives searchable as PDF/A, on CPU only, with no model to host. Pick Surya when you need layout, reading order, tables or bounding boxes as JSON, HTML or LaTeX. Surya's weights have a revenue cap on free use, while OCRmyPDF is MPL-2.0 with no such limit.

OCRmyPDFocrmypdf/ocrmypdfSuryadatalab/surya
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.0 s / page1.5 s / page
Best forSearchable PDFs from scansLayout and line-level OCR
InputsPDF, imagesPDF, images
Languages100+ languages (via Tesseract)90+ languages
Max pages per request1,000500
TablesNo✓ Yes
HandwritingNoNo
MathNoNo
Bounding boxesNo✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
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 OCRmyPDF if

  • You need validated searchable PDF/A output for archiving, with the OCR layer added without re-encoding other content where possible.
  • You want a CPU-only command-line tool that spreads work across all cores and needs no separate inference server.
  • You need Tesseract language packs covering 100+ languages under an MPL-2.0 licence with no revenue limit.

Choose Surya if

  • You need layout labels, reading order, HTML tables and KaTeX math with per-block bounding boxes from one model.
  • You want JSON, HTML, LaTeX or plain text output rather than a searchable PDF.
  • You want a 689M-parameter model that scores 83.7% on olmOCR-bench and runs on an NVIDIA GPU, CPU or Apple Silicon.

Key differences

OCRmyPDFSurya
LicenceMPL-2.0Code Apache-2.0; weights under a modified AI Pubs Open Rail-M licence, free for research, personal use and companies under $5M funding/revenue
How you run itCommand-line tool that runs locally on CPU only, using all coresLightweight client that needs a separately running vLLM or llama.cpp inference server (NVIDIA GPU, CPU or Apple Silicon)
PriceFree, self-hosted; you pay for computeFree, self-hosted; you pay for compute. A commercial licence is needed above $5M revenue or funding
Output formatsSearchable PDF (PDF/A by default) and plain text; no layout, table or Markdown outputJSON, HTML, LaTeX, bounding boxes and plain text
BenchmarksNot publishedolmOCR-bench 83.7% and OmniParseBench 85.9 (Surya 2.5, published by the authors)
Languages100+ via Tesseract language packs90+ languages; 74.9% pass rate on a 91-language test, with only 21 of 91 reaching 90%
Known failureUsing --deskew --clean-final can double or quadruple file size with worse quality; --skip-text with default PDF/A output removes form fields; hangs on PDFs whose forms share one Resources dictionarySurya 2.5 table output lacks row/column geometry; multilingual tables score 58.1; not for handwriting, photos or natural scenes

Sources

What each one is

OCRmyPDF

Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.

OCRmyPDF details

Surya

Open-source OCR toolkit with line detection, layout analysis, reading order and tables.

Surya 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": "ocrmypdf/ocrmypdf","fallbacks": ["datalab/surya"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

OCRmyPDF alternativesSurya alternativesBest OCR models in 2026