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/ocrmypdf | Suryadatalab/surya | |
|---|---|---|
| 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 | Layout and line-level OCR |
| Inputs | PDF, images | PDF, images |
| Languages | 100+ languages (via Tesseract) | 90+ languages |
| Max pages per request | 1,000 | 500 |
| Tables | No | ✓ Yes |
| Handwriting | No | No |
| Math | No | No |
| 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 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
| OCRmyPDF | Surya | |
|---|---|---|
| Licence | MPL-2.0 | Code 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 it | Command-line tool that runs locally on CPU only, using all cores | Lightweight client that needs a separately running vLLM or llama.cpp inference server (NVIDIA GPU, CPU or Apple Silicon) |
| Price | Free, self-hosted; you pay for compute | Free, self-hosted; you pay for compute. A commercial licence is needed above $5M revenue or funding |
| Output formats | Searchable PDF (PDF/A by default) and plain text; no layout, table or Markdown output | JSON, HTML, LaTeX, bounding boxes and plain text |
| Benchmarks | Not published | olmOCR-bench 83.7% and OmniParseBench 85.9 (Surya 2.5, published by the authors) |
| Languages | 100+ via Tesseract language packs | 90+ languages; 74.9% pass rate on a 91-language test, with only 21 of 91 reaching 90% |
| Known failure | Using --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 dictionary | Surya 2.5 table output lacks row/column geometry; multilingual tables score 58.1; not for handwriting, photos or natural scenes |
Sources
- OCRmyPDF GitHub README
- Issue #948 file size
- Issue #1790 form fields
- Issue #1763 hang
- Surya GitHub README
- Datalab pricing and license FAQ
What each one is
OCRmyPDF
Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.
OCRmyPDF detailsSurya
Open-source OCR toolkit with line detection, layout analysis, reading order and tables.
Surya detailsTry 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 vs dots.ocrOCRmyPDF vs ChandraRapidOCR vs SuryaEasyOCR vs SuryaSurya vs dots.ocrAmazon Textract vs SuryaSurya vs Phi-4-multimodalSurya vs Google Cloud Vision OCR
OCRmyPDF alternativesSurya alternativesBest OCR models in 2026