Azure Document Intelligence vs Chunkr
Pick Azure Document Intelligence for invoices, receipts and ID documents, especially if you already run on Azure. It has prebuilt models for them and a published table benchmark. Pick Chunkr for RAG chunking of PDFs and slides, or when you want to self-host layout parsing and do not want per-page fees.
Azure Document Intelligenceazure/document-intelligence | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | OCR API | OCR API |
| Price | 60 credits / page | 14 credits / page |
| Per 1,000 pages | $60.00 | $14.00 |
| Typical speed | 1.5 s / page | 3.0 s / page |
| Best for | Enterprise forms and IDs | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 300+ languages | Multilingual |
| Max pages per request | 2,000 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | 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 Azure Document Intelligence if
- It has prebuilt models for invoices, receipts, IDs, W-2 and contracts, so you do not train your own for those.
- Read OCR costs $1.50 per 1,000 pages, dropping to $0.60 above 1M pages.
- It scored 82.7% on RD-TableBench table accuracy, an independent benchmark, and it fits teams already on Azure.
Choose Chunkr if
- It does semantic chunking and layout analysis, and accepts PDF, PPT, Word and images, which suits RAG on PDFs and slides.
- You can self-host it with Docker on GPU, CPU-only or Mac ARM, with the open-source version free apart from compute and an LLM endpoint.
- It works with any OpenAI-compatible LLM endpoint and outputs HTML, Markdown, JSON and bounding boxes.
Key differences
| Azure Document Intelligence | Chunkr | |
|---|---|---|
| Licence | Proprietary | AGPL-3.0, or a commercial license. Closed-source products need the commercial license. |
| How you run it | Managed Azure service, or disconnected containers for on-prem use | Cloud API, or self-host via Docker. Self-host still needs an external LLM endpoint. |
| Price | Read $1.50 per 1,000 pages; Layout and prebuilt $10 per 1,000; custom extraction $30 per 1,000; 500 free pages a month | Hosted credit-based plans, official prices not verified. Open-source version is free, you pay for compute and an LLM endpoint. |
| Output formats | JSON, Markdown, plain text, bounding boxes, searchable PDF | HTML, Markdown, JSON, bounding boxes |
| Benchmark | 82.7% on RD-TableBench table accuracy (independent) | Not published |
| Prebuilt document types | Invoices, receipts, IDs, W-2 and contracts | No prebuilt document models listed. Focus is layout parsing and chunking. |
| Known limits | Stacking models multiplies cost, for example Prebuilt plus Layout plus high-res add-on is $26 per 1,000 pages. The free tier covers only the first two pages of each document. | The open-source version uses community models, less accurate than the cloud's in-house models, and does not support Excel. |
Sources
What each one is
Azure Document Intelligence
Azure layout model with tables, selection marks and prebuilt invoice and ID readers.
Azure Document Intelligence 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": "azure/document-intelligence","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Azure Document Intelligence vs ABBYY FineReaderAzure Document Intelligence vs UnstructuredGoogle Document AI vs ChunkrAmazon Textract vs ChunkrSmolDocling vs ChunkrAzure Document Intelligence vs DonutAzure Document Intelligence vs PaddleOCR-VLAzure Document Intelligence vs DeepSeek-OCR
Azure Document Intelligence alternativesChunkr alternativesBest OCR models in 2026