Azure Document Intelligence vs Docling
Pick Azure Document Intelligence for invoices, receipts and ID documents, or if you already run on Azure and want a managed service with prebuilt models. Pick Docling for RAG ingestion of born-digital PDFs and Office files, where a free MIT-licensed library that outputs structured JSON with layout is the main draw. Docling costs only compute, while Azure bills per page and the cost grows as you stack models.
Azure Document Intelligenceazure/document-intelligence | Doclingibm/docling | |
|---|---|---|
| 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 | 2.2 s / page |
| Best for | Enterprise forms and IDs | Structured export for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 300+ languages | Latin scripts, CJK |
| 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 | No |
| 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 ships prebuilt models for invoices, receipts, IDs, W-2 and contracts, so you do not train anything for those documents.
- Read OCR costs $1.50 per 1,000 pages and drops to $0.60 above 1M pages.
- Disconnected containers let you run it on-prem if you are already in the Azure ecosystem.
Choose Docling if
- It is MIT licensed and free to self-host, so your only cost is compute.
- One API parses PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails and XBRL, with lossless JSON export that keeps layout, reading order and table structure.
- You can plug in OCR backends (EasyOCR, Tesseract, RapidOCR) or VLMs such as the 258M-parameter GraniteDocling, and it integrates with LangChain and LlamaIndex.
Key differences
| Azure Document Intelligence | Docling | |
|---|---|---|
| Licence | Proprietary | MIT (individual models have their own licenses) |
| How you run it | Managed Azure service, also available as containers including disconnected on-prem | Python library that runs locally on macOS, Linux and Windows; CPU works, GPU speeds up model stages |
| 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, first two pages of each document only | Free, self-hosted (you pay for compute) |
| Output formats | JSON, Markdown, plain text, bounding boxes, searchable PDF | Markdown, HTML, JSON, DocTags, plain text |
| Table accuracy benchmark | 82.7% on RD-TableBench (independent) | Not published |
| Scanned-page quality | Not published | Depends on the OCR engine you plug in, not on Docling itself |
| Known failure | Stacking models multiplies cost: Prebuilt plus Layout plus high-res add-on is $26 per 1,000 pages | OCR regression in 2.143.1 drops words and numbers with full-page Tesseract OCR; reading order can merge neighbouring columns on some layouts |
Sources
- Azure pricing page
- Reducto RD-TableBench
- Docling GitHub README
- Supported formats
- Issue #5254 OCR regression
- Issue #5132 reading order
What each one is
Azure Document Intelligence
Azure layout model with tables, selection marks and prebuilt invoice and ID readers.
Azure Document Intelligence 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": ["ibm/docling"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Azure Document Intelligence vs TesseractAzure Document Intelligence vs MinerUGoogle Document AI vs DoclingAmazon Textract vs DoclingLlamaParse vs DoclingPaddleOCR-VL vs DoclingMinerU vs DoclingDocling vs Tesseract
Azure Document Intelligence alternativesDocling alternativesBest OCR models in 2026