OCRRouter

OCRmyPDF vs Typhoon OCR

Pick OCRmyPDF to make scanned PDF archives searchable and keep PDF/A output, such as office scanner pipelines. Pick Typhoon OCR to turn Thai or English pages into Markdown, HTML or LaTeX, such as Thai government forms and financial reports. The main split is output: OCRmyPDF adds a text layer to the PDF, while Typhoon OCR reads the page layout and tables into new text.

OCRmyPDFocrmypdf/ocrmypdfTyphoon OCRtyphoon/typhoon-ocr
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.0 s / page1.8 s / page
Best forSearchable PDFs from scansThai documents
InputsPDF, imagesPDF, images
Languages100+ languages (via Tesseract)Thai, English
Max pages per request1,000500
TablesNo✓ Yes
HandwritingNoNo
MathNoNo
Bounding boxesNoNo
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 for archiving, with the OCR layer inserted losslessly where possible.
  • You need many languages: it uses Tesseract, which covers 100+ languages via language packs.
  • You only have CPUs: it runs on CPU only and spreads work across all cores.

Choose Typhoon OCR if

  • Your documents are Thai or English, including Thai-English mixed pages, Thai books, government forms and financial reports.
  • You need structure out of the page: tables as HTML with merged cells, equations as LaTeX, and checkboxes marked.
  • You want a hosted option as well as self-hosting: weights are open, and the model is also served on the Typhoon API as typhoon-ocr-v2.

Key differences

OCRmyPDFTyphoon OCR
What it doesAdds a Tesseract OCR text layer to scanned PDFs, producing searchable PDF/ADocument OCR model that reads pages into structured text
Output formatsSearchable PDF, plain text. No layout, table or Markdown outputMarkdown, HTML, LaTeX
LicenceMPL-2.0Apache-2.0, subject to OpenTyphoon Terms and Conditions
How you run itLocal command-line tool, CPU onlySelf-hosted weights (2B, with a 0.8B V2 variant) or the Typhoon API
PriceFree, self-hosted (you pay for compute)Free, self-hosted (you pay for compute). Typhoon API pricing is not published on the model card
Languages100+ via Tesseract language packsOnly Thai and English evaluated
BenchmarksNot publishedV2 2B: olmOCR-bench 84.7, OmniDocBench v1.6 90.97, ThaiOCRBench 59.9 (authors' numbers)
Known failureFile size can double or quadruple with --deskew --clean-final (issue #948). --skip-text with default PDF/A output removes form fields (issue #1790)V2 can loop until the token limit, mostly on dense multi-column pages. Key-information extraction is weakest, at 21.0 on ThaiOCRBench

Sources

What each one is

OCRmyPDF

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

OCRmyPDF details

Typhoon OCR

Open vision model tuned for Thai and English documents, with Markdown output.

Typhoon OCR 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": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

OCRmyPDF alternativesTyphoon OCR alternativesBest OCR models in 2026