Unstructured vs Chunkr
Pick Unstructured to ingest mixed file types (PDFs, HTML, Word, PowerPoint, emails, images) for RAG, or if you want a hosted API with 10,000 free pages. Pick Chunkr if you want self-hosted layout parsing with semantic chunking and Markdown or HTML output for PDFs and slides. The main split is tables and licensing: Unstructured's open-source library scores 0.426 on table cell content against 0.866 hosted, and Chunkr's AGPL-3.0 needs a commercial license for closed products.
Unstructuredunstructured/unstructured | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | OCR API | OCR API |
| Price | 20 credits / page | 14 credits / page |
| Per 1,000 pages | $20.00 | $14.00 |
| Typical speed | 3.0 s / page | 3.0 s / page |
| Best for | Mixed file types into RAG | Layout-aware chunks for RAG |
| Inputs | PDF, images, DOCX | PDF, images, DOCX |
| Languages | Multilingual | Multilingual |
| Max pages per request | 1,000 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ 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 Unstructured if
- You need one library for PDFs, HTML, Word, PowerPoint, emails and images.
- You want to start on the hosted API for free: the first 10,000 pages cost nothing, then $0.015 per page.
- You want to trade speed for quality with the Auto, Fast, High-Res and VLM strategies, and the library is Apache-2.0 with many connectors.
Choose Chunkr if
- You want layout analysis, OCR with bounding boxes and semantic chunking in one service for PDFs, slides, Word and images.
- You want Markdown or HTML output, and a self-host setup via Docker with GPU, CPU-only and Mac ARM options.
- You already have an OpenAI-compatible LLM endpoint to point it at, and you can accept AGPL-3.0 or buy a commercial license.
Key differences
| Unstructured | Chunkr | |
|---|---|---|
| Licence | Apache-2.0 for the open-source library; proprietary for the hosted platform | AGPL-3.0 or commercial license; closed-source products need the commercial one |
| How you run it | Self-host the Python library or use the hosted API | Cloud API or open-source self-host via Docker; self-host still needs an external LLM endpoint |
| Price | Hosted: first 10,000 pages free, then $0.015 per page; Business is custom; library is free | Hosted credit-based plans, official prices not verified; open-source is free but you pay for compute and an LLM endpoint |
| Output formats | JSON, HTML, plain text, bounding boxes | HTML, Markdown, JSON, bounding boxes |
| Input file types | PDFs, HTML, Word, PowerPoint, emails and images | PDF, PPT, Word and images; Excel is not supported in the open-source version |
| Benchmark | Vendor's own table cell content score: 0.426 open-source vs 0.866 hosted | Not published |
| Known failure | hi_res tables cut off at edges and drop first letters; table OCR ignores language settings; the library sends usage telemetry by default | Open-source version uses community models, less accurate than the cloud's in-house models |
Sources
What each one is
Unstructured
Document ETL for RAG. Partitions many file types into typed elements; open-source library too.
Unstructured 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": "unstructured/unstructured","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Unstructured alternativesChunkr alternativesBest OCR models in 2026