Tesseract.js vs Chunkr
Pick Tesseract.js when you need OCR inside a browser or Node.js app and images must stay on the user's device. Pick Chunkr when you need to parse PDFs, slides and Word files into Markdown, HTML or JSON for RAG, because Tesseract.js does not accept PDF and returns no layout or Markdown.
Tesseract.jstesseract/tesseract-js | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 1 credit / page | 14 credits / page |
| Per 1,000 pages | $1.00 | $14.00 |
| Typical speed | 2.0 s / page | 3.0 s / page |
| Best for | OCR in the browser | Layout-aware chunks for RAG |
| Inputs | images | PDF, images, DOCX |
| Languages | 100+ languages | Multilingual |
| Max pages per request | 500 | 1,000 |
| Tables | No | ✓ Yes |
| Handwriting | No | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | 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 Tesseract.js if
- Runs fully client side in the browser, so images never leave the user's device.
- Apache-2.0 licence with npm, ESM and CDN script tag installs, and no closed-use restriction.
- Supports more than 100 languages through Tesseract traineddata files.
Choose Chunkr if
- Accepts PDF, PPT, Word and images, while Tesseract.js does not accept PDF.
- Returns HTML, Markdown, JSON and OCR with bounding boxes, so it suits RAG chunking of PDFs and slides.
- Offers both a cloud API and a self-host version via Docker, with GPU, CPU-only and Mac ARM options.
Key differences
| Tesseract.js | Chunkr | |
|---|---|---|
| How you run it | JavaScript and WebAssembly library in the browser or Node.js | Cloud API or self-hosted Docker (GPU, CPU-only, Mac ARM) |
| Licence | Apache-2.0 | AGPL-3.0 or commercial licence; closed-source products need the commercial licence |
| Price | Free, self-hosted on the user's device or your server | Hosted credit-based plans, prices not published; open-source version is free but you pay for compute and an LLM endpoint |
| Input formats | Images only; no PDF input (the README points to Scribe.js for PDFs) | PDF, PPT, Word and images; no Excel in the open-source version |
| Output formats | Plain text, hOCR, bounding boxes | HTML, Markdown, JSON, bounding boxes |
| Tables and layout | Not supported; no table, layout or Markdown output | Layout analysis and semantic chunking |
| Known failure | Lower accuracy than the native Tesseract CLI on the same image; fails on screen resolution text unless upscaled; one Electron user measured about 15 s per page versus 1.5 s with the CLI | Open-source version uses community models, less accurate than the cloud's in-house models; self-host still needs an external LLM endpoint |
Sources
- Tesseract.js GitHub README
- Tesseract.js issue #251 accuracy vs CLI
- Tesseract.js HN thread
- Chunkr GitHub README
- Chunkr site
What each one is
Tesseract.js
Tesseract compiled to JavaScript and WebAssembly, so OCR runs in the browser or in Node.js.
Tesseract.js 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.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
Use one, fall back to the other
{"model": "tesseract/tesseract-js","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Tesseract.js vs ABBYY FineReaderTesseract.js vs UnstructuredOpenOCR vs ChunkrFlorence-2 vs ChunkrHunyuan OCR vs ChunkrChandra vs ChunkrDeepSeek-VL2 vs ChunkrUnlimited OCR vs Chunkr
Tesseract.js alternativesChunkr alternativesBest OCR models in 2026