Azure Document Intelligence vs Hunyuan OCR
Pick Azure Document Intelligence for invoices, receipts, IDs, W-2s and contracts, where prebuilt models and a managed service save you work. Pick Hunyuan OCR if you can self-host a ~1B model and need photo text spotting, image translation or historical scripts without per-page fees. The main split is a priced managed API versus a free model you run yourself.
Azure Document Intelligenceazure/document-intelligence | Hunyuan OCRtencent/hunyuan-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 | Chinese documents and photos |
| 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 ships prebuilt models for invoices, receipts, IDs, W-2 and contracts, so you do not train your own.
- Read OCR costs $1.50 per 1,000 pages, dropping to $0.60 above 1M pages, with 500 free pages a month.
- It is available as a managed service or as disconnected containers for on-prem use, with no license region limits listed.
Choose Hunyuan OCR if
- There is no per-page fee: the model is free and you pay only for your own compute.
- One ~1B model covers document parsing, text spotting, information extraction and image translation.
- It handles low-resource and ancient-script OCR, and it runs on a laptop through the llama.cpp GGUF path.
Key differences
| Azure Document Intelligence | Hunyuan OCR | |
|---|---|---|
| How you run it | Managed Azure service, or containers including disconnected containers | Self-hosted only, via vLLM, Transformers or llama.cpp |
| Price | Read $1.50 per 1,000 pages; Layout and prebuilt $10 per 1,000; custom extraction $30 per 1,000 | Free; you pay for compute |
| Licence | Proprietary | Tencent Hunyuan Community License; excludes EU, UK and South Korea; separate license above 100M monthly active users |
| Output formats | JSON, Markdown, plain text, bounding boxes, searchable PDF | Markdown, HTML, LaTeX, JSON, plain text, bounding boxes |
| Benchmark | RD-TableBench table accuracy 82.7% | ParseBench-2 overall 67.11; ParseBench mean 63.86 (different benchmarks, not directly comparable) |
| Hardware | None to manage on the hosted service | NVIDIA GPU with CUDA 13 recommended for the unified vLLM setup; llama.cpp GGUF for CPU or consumer GPU |
| Known weak spots | 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 | Not usable in the EU, UK or South Korea under the license; archived 1.0 note said Transformers and vLLM outputs differed in accuracy |
Sources
- Azure pricing page
- Reducto RD-TableBench
- HunyuanOCR GitHub
- HunyuanOCR model card
- Hunyuan Community License
What each one is
Azure Document Intelligence
Azure layout model with tables, selection marks and prebuilt invoice and ID readers.
Azure Document Intelligence detailsHunyuan OCR
Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.
Hunyuan 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": ["tencent/hunyuan-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Azure Document Intelligence alternativesHunyuan OCR alternativesBest OCR models in 2026