Amazon Textract vs Donut
Donut is cheaper per page; Donut is faster; only Amazon Textract supports tables, handwriting, bounding boxes, confidence.
Amazon Textractaws/textract | Donutnaver/donut | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 6 credits / page | 1 credit / page |
| Per 1,000 pages | $6.00 | $1.00 |
| Typical speed | 1.2 s / page | 1.0 s / page |
| Best for | Forms and key-value extraction | Receipt and form fields after fine-tuning |
| Inputs | PDF, images | images |
| Languages | 6 languages | English, Chinese, Japanese, Korean |
| Max pages per request | 3,000 | 100 |
| Tables | ✓ Yes | No |
| Handwriting | ✓ Yes | No |
| Math | No | No |
| Bounding boxes | ✓ Yes | No |
| Confidence | ✓ Yes | No |
| Forms | ✓ Yes | ✓ Yes |
| Multilingual | No | No |
| On OCRRouter | Available | Coming soon |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
What each one is
Amazon Textract
AWS OCR with form key-value pairs, tables and per-word confidence scores.
Amazon Textract detailsDonut
OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.
Donut detailsUse one, fall back to the other
Request body
{
"model": "aws/textract",
"fallbacks": ["naver/donut"],
"file_url": "https://example.com/document.pdf"
}