OCRRouter

OCRmyPDF vs Hunyuan OCR

Pick OCRmyPDF to make scanned PDF archives searchable as PDF/A on CPU-only machines. Pick Hunyuan OCR when you need Markdown, HTML, LaTeX, JSON or bounding boxes from images and photos, and you have a GPU or can run the llama.cpp path. The main split is the output: OCRmyPDF returns a searchable PDF or plain text, Hunyuan OCR returns structured data.

OCRmyPDFocrmypdf/ocrmypdfHunyuan OCRtencent/hunyuan-ocr
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 scansChinese documents and photos
InputsPDF, imagesPDF, images
Languages100+ languages (via Tesseract)100+ languages
Max pages per request1,000500
TablesNo✓ Yes
HandwritingNoNo
MathNo✓ Yes
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 inserted without re-encoding other content where possible.
  • You only have CPU hardware, and you want work spread across all CPU cores.
  • You need 100+ languages through Tesseract language packs and an MPL-2.0 licence, with no regional restriction.

Choose Hunyuan OCR if

  • You need Markdown, HTML, LaTeX, JSON or bounding boxes instead of a text layer on a PDF.
  • You work with photo and scene text, text-image translation, or low-resource and historical scripts, which one ~1B model covers.
  • You want images up to 4K and a 128K context window in v1.5, and you can run it on a laptop through llama.cpp GGUF.

Key differences

OCRmyPDFHunyuan OCR
What it isCommand-line tool that adds a Tesseract text layer to scanned PDFs~1B end-to-end OCR vision-language model for parsing, spotting, extraction and translation
LicenceMPL-2.0Tencent Hunyuan Community License; excludes the EU, UK and South Korea, and needs a separate licence above 100M monthly active users
HardwareCPU only, uses all coresNVIDIA GPU with CUDA 13 recommended for the vLLM setup; llama.cpp GGUF path for CPU, consumer GPU or laptop
Output formatsSearchable PDF (PDF/A by default), plain textMarkdown, HTML, LaTeX, JSON, plain text, bounding boxes
Layout and tablesNo layout, table or Markdown outputDocument parsing with structured output; ParseBench-2 overall 67.11, text score 62.88
PriceFree, self-hosted (you pay for compute)Free, self-hosted (you pay for compute)
Known failureFile size can double or quadruple with --deskew --clean-final; --skip-text with PDF/A removes form fields; hangs on PDFs whose forms share one Resources dictionaryUnified setup needs CUDA 13 and vLLM 0.25.1+; an archived 1.0 note said Transformers and vLLM outputs differed in accuracy

Sources

What each one is

OCRmyPDF

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

OCRmyPDF details

Hunyuan OCR

Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.

Hunyuan 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": ["tencent/hunyuan-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

OCRmyPDF alternativesHunyuan OCR alternativesBest OCR models in 2026