Google Document AI vs Donut
Pick Google Document AI if you want a hosted API that works on day one for bulk OCR, form parsing or RAG chunking on Google Cloud. Pick Donut if you have a narrow, fixed-layout document type such as receipts or forms and can fine-tune and host the model yourself. The main split is a managed per-page service against a free MIT model that needs training before use.
Google Document AIgoogle/document-ai | Donutnaver/donut | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 10 credits / page | 1 credit / page |
| Per 1,000 pages | $10.00 | $1.00 |
| Typical speed | 1.4 s / page | 1.0 s / page |
| Best for | Multilingual scans | Receipt and form fields after fine-tuning |
| Inputs | PDF, images | images |
| Languages | 200+ languages | English, Chinese, Japanese, Korean |
| Max pages per request | 500 | 100 |
| Tables | ✓ Yes | No |
| Handwriting | ✓ Yes | No |
| Math | No | No |
| Bounding boxes | ✓ Yes | No |
| Confidence | ✓ Yes | No |
| Forms | ✓ Yes | ✓ Yes |
| 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 Google Document AI if
- It works through an API with no training step, with Enterprise Document OCR at $1.50 per 1,000 pages and $0.60 above 5M pages a month.
- Layout Parser includes chunking for RAG at $10 per 1,000 pages, and batch requests take up to 500 pages.
- It returns JSON, plain text, bounding boxes and chunks, while Donut outputs only JSON and plain text.
Choose Donut if
- It is MIT licensed and free to run, so you pay only for your own compute.
- It maps document images straight to structured output with no separate OCR step, which suits receipt and form field extraction after fine-tuning.
- You own the model and can fine-tune it on your own layouts, and a Hacker News practitioner reports about 200 documents can reach human-level accuracy on narrow data.
Key differences
| Google Document AI | Donut | |
|---|---|---|
| Deployment | Hosted API on Google Cloud | Self-hosted |
| Licence | Proprietary | MIT |
| Price | Enterprise Document OCR $1.50 per 1,000 pages ($0.60 above 5M a month, first 1,000 free); Layout Parser $10; Form Parser $30 per 1,000 pages | Free, you pay for compute |
| Ready to use | Yes, through the API | No. The base checkpoint is pretrain-only and must be fine-tuned |
| Output formats | JSON, plain text, bounding boxes, chunks | JSON, plain text |
| Size limits | Online requests up to 15 pages (30 in imageless mode); batch up to 500 pages; Form Parser batch up to 100 pages | Misses tiny text in large images because of input resolution limits |
| Benchmark | 64.6% on RD-TableBench, behind Azure and Textract | Not published |
Sources
- Document AI pricing
- Document AI limits
- Reducto RD-TableBench
- donut-base model card
- Donut ECCV paper
- Hacker News thread
What each one is
Google Document AI
Google Cloud OCR with layout parsing and specialised processors.
Google Document AI detailsDonut
OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.
Donut 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": "google/document-ai","fallbacks": ["naver/donut"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Google Document AI vs GOT-OCR 2.0Google Document AI vs NougatDeepSeek-OCR vs DonutAzure Document Intelligence vs DonutGoogle Document AI vs Tesseract.jsGoogle Document AI vs MinerUGoogle Document AI vs DoclingDonut vs Tesseract.js
Google Document AI alternativesDonut alternativesBest OCR models in 2026