OCRmyPDF vs Chunkr
Pick OCRmyPDF to make scanned PDFs searchable and keep them as PDF/A, for example office scanner output or archives. Pick Chunkr when you need Markdown, HTML, JSON or bounding boxes from PDFs, slides and Word files, for example to chunk documents for RAG. The main split is that OCRmyPDF only adds a text layer, while Chunkr parses layout and returns structured output.
OCRmyPDFocrmypdf/ocrmypdf | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 1 credit / page | 14 credits / page |
| Per 1,000 pages | $1.00 | $14.00 |
| Typical speed | 1.0 s / page | 3.0 s / page |
| Best for | Searchable PDFs from scans | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 100+ languages (via Tesseract) | Multilingual |
| Max pages per request | 1,000 | 1,000 |
| 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, and the OCR layer is inserted losslessly where possible.
- You want a CPU-only tool that runs locally, spreads work across all cores and is free under MPL-2.0.
- You need Tesseract's 100+ languages through language packs.
Choose Chunkr if
- You need HTML, Markdown, JSON and OCR bounding boxes, not just a searchable PDF.
- You are chunking PDFs, PPT, Word files or images for RAG and want layout analysis.
- You want a choice between a hosted API and a Docker self-host with GPU, CPU-only or Mac ARM options, and you can work with an OpenAI-compatible LLM endpoint.
Key differences
| OCRmyPDF | Chunkr | |
|---|---|---|
| What it does | Adds a Tesseract OCR text layer to scanned PDFs. No layout, table or Markdown output. | Layout analysis, OCR with bounding boxes and semantic chunking. |
| Output formats | Searchable PDF (PDF/A by default) and plain text. | HTML, Markdown, JSON and bounding boxes. |
| Licence | MPL-2.0. | AGPL-3.0 or a commercial licence. Closed-source use needs the commercial licence. |
| How you run it | Command-line tool that runs locally. CPU only. | Cloud API, or self-host with Docker (GPU, CPU-only, Mac ARM). Self-host needs an external LLM endpoint. |
| Price | Free. You pay for compute. | Hosted: credit-based plans, price not published. Open-source version is free; you pay for compute and an LLM endpoint. |
| Input files | Scanned PDFs. | PDF, PPT, Word and images. Excel is not supported in the open-source version. |
| Known failure | Accuracy is capped by Tesseract. --deskew --clean-final can double or quadruple file size (issue #948), and --skip-text with default PDF/A output removes form fields (issue #1790). | The open-source version uses community models that are less accurate than the cloud's in-house models. |
Sources
- OCRmyPDF GitHub README
- OCRmyPDF docs
- Issue #948 file size
- Issue #1790 form fields
- GitHub README
- Chunkr site
What each one is
OCRmyPDF
Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.
OCRmyPDF detailsChunkr
Document parsing API that segments and chunks pages for RAG. Self-hostable version available.
Chunkr 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": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
OCRmyPDF alternativesChunkr alternativesBest OCR models in 2026