Azure Document Intelligence vs dots.ocr
Pick Azure Document Intelligence for invoices, receipts and ID documents, especially if you already run on Azure and want a managed API with prebuilt models. Pick dots.ocr if you want to self-host an MIT-licensed model and turn multilingual PDFs into Markdown with layout, and you are fine paying only for GPU compute. The main split is a priced managed service versus a free model you must run and tune yourself.
Azure Document Intelligenceazure/document-intelligence | dots.ocrrednote/dots-ocr | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 60 credits / page | 2 credits / page |
| Per 1,000 pages | $60.00 | $2.00 |
| Typical speed | 1.5 s / page | 1.5 s / page |
| Best for | Enterprise forms and IDs | Multilingual document parsing |
| Inputs | PDF, images | PDF, images |
| Languages | 300+ languages | 100+ languages |
| Max pages per request | 2,000 | 500 |
| 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 extraction for those types.
- Read OCR costs $1.50 per 1,000 pages, dropping to $0.60 above 1M pages, with no GPU to run.
- Disconnected containers are available if you need on-prem use, and it scored 82.7% on RD-TableBench, an independent table test.
Choose dots.ocr if
- The code is MIT-licensed and free to use, so you pay only for compute, not per page.
- One 3B model returns layout boxes, categories and text in a single pass, with tables as HTML and formulas as LaTeX.
- The dots.mocr (v1.5) release scores 83.9 on olmOCR-bench, up from 79.1 for the original, and the dots.mocr-svg variant converts charts and diagrams to SVG.
Key differences
| Azure Document Intelligence | dots.ocr | |
|---|---|---|
| How you run it | Managed Azure service, or containers including disconnected ones for on-prem | Self-hosted via vLLM or Hugging Face Transformers; a single CUDA GPU with vLLM is the documented path |
| Licence | Proprietary | MIT, with a separate dots.ocr license agreement file in the repository |
| Price | Read $1.50 per 1,000 pages; Layout and prebuilt $10 per 1,000; custom extraction $30 per 1,000; 500 free pages per month | Free; you pay for compute |
| Output formats | JSON, Markdown, plain text, bounding boxes, searchable PDF | JSON, Markdown, HTML, LaTeX, bounding boxes, SVG |
| Benchmarks | 82.7% on RD-TableBench (independent) | 79.1 on olmOCR-bench for dots.ocr and 83.9 for dots.mocr (reported by the authors) |
| Prebuilt document types | Invoices, receipts, IDs, W-2 and contracts | Not published |
| Known failure | Stacking models multiplies cost: 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 | Runs of ellipses or underscores can make output repeat endlessly, and a table above 1000 grid cells can drop the whole page in Docling |
Sources
- Azure pricing page
- Azure DI pricing breakdown
- Reducto RD-TableBench
- dots.ocr GitHub README
- Docling issue #5146
What each one is
Azure Document Intelligence
Azure layout model with tables, selection marks and prebuilt invoice and ID readers.
Azure Document Intelligence detailsdots.ocr
Single vision model from rednote that does layout detection and content recognition together.
dots.ocr 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": "azure/document-intelligence","fallbacks": ["rednote/dots-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Azure Document Intelligence alternativesdots.ocr alternativesBest OCR models in 2026