Donut OCR online
OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
- Model ID
- naver/donut
- Type
- Open source
- Price
- 1 credit / page ($1.00 per 1,000 pages)
- Typical speed
- 1.0 s / page
- Inputs
- images
- Languages
- English, Chinese, Japanese, Korean
- Max pages per request
- 100
- Output
- Markdown, JSON
- License
- MIT
- Supports
- Forms
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "naver/donut",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'Donut speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
Donut pricing
Donut costs 1 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $1.00. You only pay for pages that return a result.
New accounts get 50 free credits, enough for about 50 pages with this model. See pricing for credit packs.
Similar models
1Nanonets-OCROpen image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.
nanonets/nanonets-ocr2 credits / page2TrOCRTransformer text recognition model. Reads single text lines, including handwriting.microsoft/trocr1 credit / page3Llama 3.2 11B VisionMeta's smaller Llama 3.2 vision model (September 2024).meta/llama-3-2-11b-vision1 credit / pageAll Donut alternativesBest OCR models by use case
Compare Donut
Donut vs Nanonets-OCRDonut vs TrOCRDonut vs Llama 3.2 11B VisionDonut vs PaddleOCR-VLDonut vs ChandraDonut vs GPT-5 mini