Azure Document Intelligence vs Unlimited OCR
Pick Azure Document Intelligence for invoices, receipts, IDs, W-2s and contracts, or if you already run on Azure and want a managed service with prebuilt models. Pick Unlimited OCR for long reports and books, bulk PDF to text for RAG, and self-hosting under an MIT licence, as long as you can supply an NVIDIA GPU and tolerate occasional repetition or hallucinated text.
Azure Document Intelligenceazure/document-intelligence | Unlimited OCRbaidu/unlimited-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 | 1.2 s / page |
| Best for | Enterprise forms and IDs | Books and very long documents |
| Inputs | PDF, images | PDF, images |
| Languages | 300+ languages | 30+ languages |
| 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 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, with no GPU to manage.
- Disconnected containers are available for on-prem use, and it also offers a searchable PDF output.
Choose Unlimited OCR if
- It is MIT licensed and free to self-host, so you pay only for compute and can use it commercially with no copyleft.
- It parses 40+ pages in a single forward pass with roughly constant memory, which suits long reports and books.
- It emits block types and bounding boxes alongside Markdown and plain text, which helps layout-aware extraction for RAG.
Key differences
| Azure Document Intelligence | Unlimited OCR | |
|---|---|---|
| Licence | Proprietary | MIT |
| How you run it | Managed Azure service, or containers including disconnected on-prem | Self-host with vLLM, SGLang or transformers; also hosted in Baidu Cloud's OCR product |
| Price | Read $1.50 per 1,000 pages ($0.60 above 1M); Layout and prebuilt $10 per 1,000; custom extraction $30 per 1,000; 500 free pages per month | Free to self-host, you pay for compute; hosted price Not published |
| Output formats | JSON, Markdown, plain text, bounding boxes, searchable PDF | Markdown, plain text, bounding boxes |
| Benchmark | 82.7% on RD-TableBench table accuracy (independent) | 46.17 ParseBench mean (independent); Unlimited OCR 2 scores 77.1 on MarathonDocBench (by its authors) |
| Hardware | None to manage in the hosted service | NVIDIA GPU with CUDA 12.9 or 13.0; Unlimited-OCR-2 under SGLang runs out of memory on 12 GB GPUs; no CPU-only use |
| Known failure | Stacked models multiply cost, e.g. 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 | Text repetition and looping on some pages, reported hallucinated text, bold and italic styling mostly lost, context capped at 32,768 tokens |
Sources
- Azure pricing page
- Reducto RD-TableBench
- Hugging Face model card
- MarkTechPost on Unlimited OCR 2
- Issue #55 repetition
- Issue #116 OOM on 12 GB
What each one is
Azure Document Intelligence
Azure layout model with tables, selection marks and prebuilt invoice and ID readers.
Azure Document Intelligence detailsUnlimited OCR
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Unlimited 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": ["baidu/unlimited-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Azure Document Intelligence alternativesUnlimited OCR alternativesBest OCR models in 2026