Azure Document Intelligence vs Chandra
Pick Azure Document Intelligence for invoices, receipts and ID documents, especially if you already run on Azure and want prebuilt models plus a managed service. Pick Chandra for multilingual scanned documents and PDF to Markdown for RAG, where you want open weights you can self-host. The main split is the licence and cost model: Azure is proprietary and billed per page, Chandra is free to self-host under $2M funding or revenue.
Azure Document Intelligenceazure/document-intelligence | Chandradatalab/chandra | |
|---|---|---|
| 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 | 2.0 s / page |
| Best for | Enterprise forms and IDs | Complex layouts and handwriting |
| Inputs | PDF, images | PDF, images |
| Languages | 300+ languages | 40+ languages |
| Max pages per request | 2,000 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | ✓ Yes |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| Forms | ✓ Yes | ✓ Yes |
| 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.
- Read OCR costs $1.50 per 1,000 pages, dropping to $0.60 above 1M pages.
- Disconnected containers let you run it on-prem inside an Azure-centred setup.
Choose Chandra if
- Chandra 2 scores 85.8 on olmOCR-bench and averages 77.8% across 43 languages, per the authors.
- You can self-host the open weights on a single NVIDIA GPU with vLLM, free within licence terms.
- The hosted Datalab API starts at $1 per 1,000 pages, and it outputs Markdown, HTML and JSON with bounding boxes.
Key differences
| Azure Document Intelligence | Chandra | |
|---|---|---|
| Licence | Proprietary | Code Apache-2.0; weights modified OpenRAIL-M, free under $2M funding or revenue, commercial licence above that |
| How you run it | Managed Azure service, or containers including disconnected on-prem | Self-host with vLLM or Hugging Face, or use the hosted Datalab API |
| Price | Read $1.50 per 1,000 pages; Layout and prebuilt $10; custom extraction $30; 500 free pages per month | Self-hosted free within licence (you pay for compute); API $1, $3 or $7.50 per 1,000 pages; $20/month free tier |
| Output formats | JSON, Markdown, plain text, bounding boxes, searchable PDF | Markdown, HTML, JSON, bounding boxes |
| Benchmark | 82.7% on RD-TableBench table accuracy (independent) | 85.8 on olmOCR-bench (Chandra 2, authors' figure) |
| Prebuilt document types | Invoices, receipts, IDs, W-2 and contracts | Not published |
| Known failure | Stacked models multiply cost: Prebuilt plus Layout plus high-res add-on is $26 per 1,000 pages; free tier covers only the first two pages of each document | Token-loop hallucinations reported on 5-6 of about 60 Russian/Kazakh scans; weak on Urdu (43.2%) and Sanskrit (51.1%); Old Scans only 51.1 on olmOCR-bench |
Sources
- Azure pricing page
- Azure DI pricing breakdown
- Reducto RD-TableBench
- Chandra GitHub README
- Datalab pricing
- GitHub issue #51 token loops
What each one is
Azure Document Intelligence
Azure layout model with tables, selection marks and prebuilt invoice and ID readers.
Azure Document Intelligence detailsChandra
Datalab's OCR model that keeps layout and handles forms, tables and handwriting.
Chandra 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": ["datalab/chandra"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Azure Document Intelligence alternativesChandra alternativesBest OCR models in 2026