OCRmyPDF vs dots.ocr
Pick OCRmyPDF to make scanned PDF archives searchable as PDF/A on CPU-only machines. Pick dots.ocr when you need Markdown, layout boxes, HTML tables or LaTeX formulas out of PDFs and can run a CUDA GPU. They solve different problems: one adds a text layer, the other parses document structure.
OCRmyPDFocrmypdf/ocrmypdf | dots.ocrrednote/dots-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 | Multilingual document parsing |
| 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
- It outputs validated searchable PDF/A by default, which suits archiving and compliance workflows.
- It runs on CPU only and spreads work across all CPU cores, so no GPU is needed.
- It uses Tesseract, so it covers 100+ languages through language packs.
Choose dots.ocr if
- It returns layout boxes, categories and text in one pass, with tables as HTML and formulas as LaTeX.
- It outputs JSON, Markdown, HTML, LaTeX, bounding boxes and SVG, where OCRmyPDF only gives searchable PDF and plain text.
- The v1.5 model (dots.mocr) scores 83.9 on olmOCR-bench, up from 79.1 for the original, as reported by the authors.
Key differences
| OCRmyPDF | dots.ocr | |
|---|---|---|
| What it does | Adds a Tesseract text layer to scanned PDFs | Document parsing VLM that outputs layout, text, tables and formulas |
| Output formats | Searchable PDF (PDF/A) and plain text | JSON, Markdown, HTML, LaTeX, bounding boxes, SVG |
| Hardware | CPU only, uses all cores | Single CUDA GPU with vLLM is the documented path; no VRAM figure stated; not for CPU-only production |
| Licence | MPL-2.0 | MIT, with a separate dots.ocr license agreement file in the repository |
| Price | Free, self-hosted (you pay for compute) | Free, self-hosted (you pay for compute) |
| Benchmarks | Not published | olmOCR-bench 79.1 (dots.ocr), 83.9 (dots.mocr); OmniDocBench v1.5 text edit distance 0.031 (dots.mocr, lower is better); all by the authors |
| Known failure | --skip-text with default PDF/A output removes form fields (issue #1790); file size can double or quadruple with --deskew --clean-final (issue #948) | Runs of ellipses or underscores can make output repeat endlessly; a table above 1000 grid cells raises an error and drops the whole page (Docling issue #5146) |
Sources
- OCRmyPDF GitHub README
- Issue #948 file size
- Issue #1790 form fields
- dots.ocr GitHub README
- dots.ocr blog / limitations
- Docling issue #5146
What each one is
OCRmyPDF
Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.
OCRmyPDF detailsdots.ocr
Single vision model from rednote that does layout detection and content recognition together.
dots.ocr 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": ["rednote/dots-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
OCRmyPDF vs Nanonets-OCROCRmyPDF vs SuryaRapidOCR vs dots.ocrEasyOCR vs dots.ocrdots.ocr vs InternVL3.5OCRmyPDF vs KrakenOCRmyPDF vs TrOCROCRmyPDF vs Adobe Acrobat OCR
OCRmyPDF alternativesdots.ocr alternativesBest OCR models in 2026