Nanonets-OCR vs Chunkr
Pick Nanonets-OCR if you want a small 3B model you host yourself to turn printed business documents into Markdown, with signatures, checkboxes and flowcharts tagged. Pick Chunkr if you need a layout-parsing pipeline that takes PDF, PPT, Word and images and returns chunks with bounding boxes, via a cloud API or a self-hosted stack. The main split is model versus service: Nanonets-OCR is one model with a fixed prompt, while Chunkr is a parsing service that also needs an LLM endpoint when self-hosted.
Nanonets-OCRnanonets/nanonets-ocr | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 2 credits / page | 14 credits / page |
| Per 1,000 pages | $2.00 | $14.00 |
| Typical speed | 1.8 s / page | 3.0 s / page |
| Best for | Markdown with semantic tags | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | Multilingual | Multilingual |
| Max pages per request | 500 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | No |
| Forms | ✓ Yes | 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 Nanonets-OCR if
- You want signatures, watermarks and image descriptions tagged, and checkboxes converted to unicode symbols.
- You need flowcharts or org charts extracted as Mermaid code, or LaTeX output that separates inline and display equations.
- You want a single 3B model to run on your own hardware, with a published DocVQA score of 89.43 and olmOCR-bench overall of 69.5 for OCR2-3B.
Choose Chunkr if
- You are building RAG over PDFs, slides and Word files and want semantic chunking with bounding boxes.
- You want a hosted API option and a self-host option from the same product, with Docker setups for GPU, CPU-only and Mac ARM.
- You already have an OpenAI-compatible LLM endpoint and want layout analysis wrapped around it.
Key differences
| Nanonets-OCR | Chunkr | |
|---|---|---|
| What it is | Open image-to-Markdown model, fine-tuned from Qwen2.5-VL-3B | Document parsing service with layout analysis, OCR and semantic chunking |
| How you run it | Self-host the weights from Hugging Face | Cloud API, or self-host with Docker |
| Licence | Not stated on the Nanonets-OCR2-3B model card | AGPL-3.0 or commercial licence; closed-source use needs the commercial one |
| Price | Free, you pay for compute | Hosted credit-based plans (prices not verified); open-source version free, you pay for compute and an LLM endpoint |
| Output formats | Markdown, HTML, LaTeX, Mermaid | HTML, Markdown, JSON, bounding boxes |
| Input types | Not published | PDF, PPT, Word and images; no Excel in the open-source version |
| Known failure | Trained on a fixed prompt, so other prompts can hallucinate; not trained on handwriting, with generation loops seen in a handwriting test | Open-source version uses community models that are less accurate than the cloud's in-house models |
Sources
- Nanonets-OCR2-3B model card
- Nanonets-OCR-s announcement
- HF discussion fixed prompt
- Chunkr GitHub README
- Chunkr site
What each one is
Nanonets-OCR
Open image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.
Nanonets-OCR 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": "nanonets/nanonets-ocr","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Nanonets-OCR alternativesChunkr alternativesBest OCR models in 2026