Nougat vs Chunkr
Pick Nougat only for non-commercial work on English arXiv-style papers where you need LaTeX math and tables out. Pick Chunkr for anything commercial or any mix of PDF, PPT, Word and images, where you want HTML, Markdown or JSON with bounding boxes for RAG chunking. The main split is licence and scope: Nougat's weights are CC-BY-NC and built for scientific papers, while Chunkr is a general layout parser with a cloud API and an AGPL self-host option.
Nougatmeta/nougat | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 2 credits / page | 14 credits / page |
| Per 1,000 pages | $2.00 | $14.00 |
| Typical speed | 3.0 s / page | 3.0 s / page |
| Best for | arXiv-style papers | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | Mainly English | Multilingual |
| Max pages per request | 200 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | No | ✓ 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 Nougat if
- Your input is English scientific papers, since it was trained on arXiv and PubMed Central documents.
- You need equations and tables as LaTeX inside Mathpix-compatible .mmd Markdown.
- Your use is non-commercial and you want a free, self-hosted Python package with small and base checkpoints, a simple CLI and an API.
Choose Chunkr if
- You are building a commercial product, since you can get a commercial licence or use the hosted cloud API, whereas Nougat's weights bar commercial use.
- You process PDF, PPT, Word and images and need HTML, Markdown or JSON with bounding boxes, plus semantic chunking for RAG.
- You want to self-host with Docker on GPU, CPU-only or Mac ARM, and can point it at any OpenAI-compatible LLM endpoint.
Key differences
| Nougat | Chunkr | |
|---|---|---|
| Licence | Code MIT; weights CC-BY-NC (no commercial use) | AGPL-3.0 or commercial licence |
| How you run it | Self-hosted Python package only | Cloud API or self-hosted via Docker (GPU, CPU-only, Mac ARM) |
| Price | Free for non-commercial use; you pay for compute | Hosted credit-based plans (official prices not verified); open-source version is free, you pay for compute and an LLM endpoint |
| Output formats | Markdown (Mathpix-style .mmd) and LaTeX | HTML, Markdown, JSON and OCR with bounding boxes |
| Input documents | Scientific PDF pages; best on English arXiv-style papers | PDF, PPT, Word and images; Excel not supported in the open-source version |
| Languages | Works best on English; Chinese, Russian and Japanese do not work | Not published |
| Known failure | Repetition loops on 1.5% of test pages in the paper, more on out-of-domain documents; looping pages can be dropped as MISSING_PAGE | Open-source version uses community models that are less accurate than the cloud's in-house models; self-host still needs an external LLM endpoint |
Sources
What each one is
Chunkr
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": "meta/nougat","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Nougat alternativesChunkr alternativesBest OCR models in 2026