Azure Document Intelligence vs MinerU
Pick Azure Document Intelligence for invoices, receipts, IDs and other forms where you want a managed API with prebuilt models, or where you already run on Azure. Pick MinerU for academic papers and mixed PDF and Office corpora that you want to convert to Markdown or JSON on your own hardware at no licence cost. The main split is managed, per-page pricing versus self-hosted, free software where you pay for compute.
Azure Document Intelligenceazure/document-intelligence | MinerUopendatalab/mineru | |
|---|---|---|
| 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 | Academic PDFs |
| Inputs | PDF, images | PDF, images |
| Languages | 300+ languages | 80+ 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 anything for those forms.
- It is a managed service with per-page pricing, and disconnected containers exist if you need on-prem use.
- It scored 82.7% on RD-TableBench table accuracy, an independent result, while MinerU's published tables have known header-row failures.
Choose MinerU if
- It is free and self-hosted, so you pay only for compute and no per-page fee applies.
- It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML, and renders to Markdown, HTML, LaTeX, DOCX, EPUB and JSON.
- Its basic tier runs on CPU with about 2 GB RAM, and the VLM tier reaches 2.12 pages per second on one A100 with vLLM.
Key differences
| Azure Document Intelligence | MinerU | |
|---|---|---|
| How you run it | Managed Azure service, also available as containers | Self-host only: CLI, API or WebUI |
| Licence | Proprietary | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 |
| 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; you pay for compute |
| Hardware | Not published | Basic tier: CPU, 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM |
| Input and output | Outputs JSON, Markdown, plain text, bounding boxes, searchable PDF | Reads PDF, images and Office files; outputs Markdown, HTML, LaTeX, DOCX, EPUB, JSON |
| Benchmark | RD-TableBench table accuracy 82.7% | olmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5) |
| Known failure | Stacked models multiply 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 | VLM tiers drop merged header rows in tables such as bank statement account lines; the VLM pipeline can produce repeated content, such as 300 KB figure blocks |
Sources
- Azure pricing page
- Reducto RD-TableBench
- MinerU GitHub README
- MinerU2.5 model card
- olmOCR-Bench table
- Issue #5554 table header rows
What each one is
Azure Document Intelligence
Azure layout model with tables, selection marks and prebuilt invoice and ID readers.
Azure Document Intelligence detailsMinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU 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": ["opendatalab/mineru"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Azure Document Intelligence alternativesMinerU alternativesBest OCR models in 2026