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/ocrmypdf | Typhoon OCRtyphoon/typhoon-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 | 1.8 s / page |
| Best for | Searchable PDFs from scans | Thai documents |
| Inputs | PDF, images | PDF, images |
| Languages | 100+ languages (via Tesseract) | Thai, English |
| Max pages per request | 1,000 | 500 |
| Tables | No | ✓ Yes |
| Handwriting | No | No |
| Math | No | No |
| Bounding boxes | No | No |
| 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 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
| OCRmyPDF | Typhoon OCR | |
|---|---|---|
| What it does | Adds a Tesseract OCR text layer to scanned PDFs, producing searchable PDF/A | Document OCR model that reads pages into structured text |
| Output formats | Searchable PDF, plain text. No layout, table or Markdown output | Markdown, HTML, LaTeX |
| Licence | MPL-2.0 | Apache-2.0, subject to OpenTyphoon Terms and Conditions |
| How you run it | Local command-line tool, CPU only | Self-hosted weights (2B, with a 0.8B V2 variant) or the Typhoon API |
| Price | Free, self-hosted (you pay for compute) | Free, self-hosted (you pay for compute). Typhoon API pricing is not published on the model card |
| Languages | 100+ via Tesseract language packs | Only Thai and English evaluated |
| Benchmarks | Not published | V2 2B: olmOCR-bench 84.7, OmniDocBench v1.6 90.97, ThaiOCRBench 59.9 (authors' numbers) |
| Known failure | File 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
- OCRmyPDF GitHub README
- OCRmyPDF docs
- Issue #948 file size
- Issue #1790 form fields
- Typhoon OCR V2 2B model card
- Typhoon OCR technical report
What each one is
OCRmyPDF
Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.
OCRmyPDF detailsTyphoon OCR
Open vision model tuned for Thai and English documents, with Markdown output.
Typhoon 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": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
OCRmyPDF alternativesTyphoon OCR alternativesBest OCR models in 2026