olmOCR vs Chunkr
Pick olmOCR when you need clean Markdown from PDFs at scale and have an NVIDIA GPU with 12 GB or more. It is Apache-2.0 and scores 82.4 on olmOCR-Bench. Pick Chunkr when you need layout, bounding boxes and semantic chunks for RAG, or when your inputs include slides and Word files. Check the AGPL-3.0 terms first if the product is closed source.
olmOCRallenai/olmocr | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 2 credits / page | 14 credits / page |
| Per 1,000 pages | $2.00 | $14.00 |
| Typical speed | 1.5 s / page | 3.0 s / page |
| Best for | Bulk PDF to text for datasets | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | Mainly English | Multilingual |
| Max pages per request | 1,000 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | 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 olmOCR if
- It scores 82.4 on olmOCR-Bench, above Marker (76.1), MinerU 2.5.4 (75.2) and Mistral OCR (72.0) in the same table.
- Self-hosting costs under $200 per million pages according to Ai2, and the toolkit is Apache-2.0 with open weights, training data and code.
- It handles equations, tables and handwriting, and strips headers and footers in natural reading order, which suits academic papers and mixed printed and handwritten pages.
Choose Chunkr if
- It returns HTML, Markdown and JSON with OCR bounding boxes, and it does layout analysis and semantic chunking for RAG.
- It accepts PDF, PPT, Word and images, so slides and Word files need no conversion first.
- It self-hosts through Docker with GPU, CPU-only and Mac ARM options, and works with any OpenAI-compatible LLM endpoint.
Key differences
| olmOCR | Chunkr | |
|---|---|---|
| Licence | Apache-2.0 (toolkit) | AGPL-3.0 or commercial licence; closed-source use needs the commercial licence |
| How you run it | Self-host with vLLM on an NVIDIA GPU, or use third-party hosted endpoints | Hosted cloud API, or self-host with Docker (GPU, CPU-only or Mac ARM); self-host still needs an external LLM endpoint |
| Hardware | NVIDIA GPU with at least 12 GB VRAM and 30 GB free disk; no CPU-only use | CPU-only self-host is available |
| Price | Under $200 per million pages self-hosted (Ai2); hosted olmOCR-2-7B on DeepInfra at $0.09 input / $0.19 output per million tokens | Hosted credit-based plans, prices not published here; open-source version is free but you pay for compute and an LLM endpoint |
| Output formats | Markdown, JSON | HTML, Markdown, JSON, bounding boxes |
| Input formats | PDFs and images | PDF, PPT, Word and images; no Excel in the open-source version |
| Benchmark | 82.4 on olmOCR-Bench (v0.4.0) | Not published |
Sources
What each one is
olmOCR
Open-source vision model from Ai2 (often searched as olm ocr) that turns PDFs into clean, reading-order text. Latest release: olmOCR 2.
olmOCR 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": "allenai/olmocr","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
olmOCR alternativesChunkr alternativesBest OCR models in 2026