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/ocrmypdf | Hunyuan OCRtencent/hunyuan-ocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credit / page | 2 credits / page |
| Per 1,000 pages | $1.00 | $2.00 |
| Typical speed | 1.0 s / page | 1.5 s / page |
| Best for | Searchable PDFs from scans | Chinese documents and photos |
| Inputs | PDF, images | PDF, images |
| Languages | 100+ languages (via Tesseract) | 100+ languages |
| Max pages per request | 1,000 | 500 |
| Tables | No | ✓ Yes |
| Handwriting | No | No |
| Math | No | ✓ Yes |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
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
| OCRmyPDF | Hunyuan OCR | |
|---|---|---|
| What it is | Command-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 |
| Licence | MPL-2.0 | Tencent Hunyuan Community License; excludes the EU, UK and South Korea, and needs a separate licence above 100M monthly active users |
| Hardware | CPU only, uses all cores | NVIDIA GPU with CUDA 13 recommended for the vLLM setup; llama.cpp GGUF path for CPU, consumer GPU or laptop |
| Output formats | Searchable PDF (PDF/A by default), plain text | Markdown, HTML, LaTeX, JSON, plain text, bounding boxes |
| Layout and tables | No layout, table or Markdown output | Document parsing with structured output; ParseBench-2 overall 67.11, text score 62.88 |
| Price | Free, self-hosted (you pay for compute) | Free, self-hosted (you pay for compute) |
| Known failure | File 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 dictionary | Unified setup needs CUDA 13 and vLLM 0.25.1+; an archived 1.0 note said Transformers and vLLM outputs differed in accuracy |
Sources
- OCRmyPDF GitHub README
- Issue #948 file size
- Issue #1790 form fields
- HunyuanOCR model card
- Hunyuan Community License
What each one is
OCRmyPDF
Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.
OCRmyPDF detailsHunyuan OCR
Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.
Hunyuan OCR detailsTry both on your own file
Run the file once with each model and compare the output.
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