Donut Document
donut-documentNaver CLOVA Donut OCR-free document-understanding transformer. End-to-end JSON extraction from forms, receipts and invoices without explicit OCR.
- Price
- ≈ US$0.0648/run
- Input → output
- Text + Image → Text
- Developer
- Community
- Updated
- September 23, 2026
Playground
Try Donut Document
No input form
No input form for this model yet
Its inputs are not documented yet. So that no run fails on a wrong input, we don't offer a form here. Pick a comparable model instead.
Examples
InputNo text prompt: the model only takes the input shown.
Response
{'menu': [{'nm': 'ICE BLAOKCOFFE', 'cnt': '2', 'price': '82,000'}, {'nm': 'AVOCADO COFFEE', 'cnt': '1', 'price': '61,000'}, {'nm': 'Oud CHINEN KATSU FF', 'cnt': '1', 'price': '51,000'}], 'sub_total': {'subtotal_price': '194,000', 'discount_price': '19,400'}, 'total': {'total_price': '174,600', 'cashprice': '200,000', 'changeprice': '25,400'}}
InputNo text prompt: the model only takes the input shown.
Response
{'menu': [{'nm': '0571-1854 BLUS WANITA', 'unitprice': '@120,000', 'cnt': '1', 'price': '120,000'}, {'nm': '1002-0060 SHOPPING BAG', 'cnt': '1', 'price': '0'}], 'total': {'total_price': '120,000', 'changeprice': '0', 'creditcardprice': '120,000', 'menuqty_cnt': '1'}}
About Donut Document
Donut Document is a model by Community in the Multimodal category. On Railwail, Donut Document costs ≈ US$0.0648 per run.
Pricing
| Typical run (≈ 240 s on T4) | US$0.0648 per run |
|---|---|
| GPU time (T4) | US$0.00027 per GPU second |
- Billed by the GPU time the run actually takes. When the run starts, 3× the typical price is reserved from your balance and settled afterwards.
- 1 credit = US$0.01
Cost calculator
Price calculator
Typical according to the provider: about 240 s
Total
US$6.48
648 credits
Per run
US$0.0648 · 6.48 credits
Billed by the actual GPU time; this is an estimate.
API
No verified API example
The public API passes a different input format than this model needs. Use the playground above.
Specifications
- Model ID
donut-document- Developer
- Community
- Category
- Multimodal
- Input
- Text, Image
- Output
- Text
- Billing
- By usage (tokens or GPU time)
- Catalog entry updated
- September 23, 2026
Tags
- replicate
- ocr
- vision-understanding
- naver
- open-source
Frequently asked questions
What is Donut Document?
Donut Document is a model by Community in the Multimodal category.
How much does Donut Document cost on Railwail?
On Railwail, Donut Document costs ≈ US$0.0648 per run. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals US$0.01.
How fast is Donut Document?
There are not enough measured runs of Donut Document on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.
Is Donut Document better than BLIP?
That depends on the task. Donut Document (Community) and BLIP (Salesforce) are both models in the Multimodal category. The comparison page shows their prices and specifications side by side.
Compare Donut Document and BLIPCan Donut Document process images?
Yes. Donut Document accepts images as input in addition to text.
Comparable models
All in this category- BLIPSalesforce
Salesforce BLIP. Vision-language model for image captioning and visual question answering. Given an image it writes a short natural-language caption, or answers a question about the image when one is supplied. A widely used baseline for automatic captioning.
- CLIP InterrogatorCommunity
pharmapsychotic's CLIP Interrogator. Takes an image and produces a Stable-Diffusion-style text prompt by combining BLIP captioning with CLIP to rank likely subjects, artists, mediums and styles. Commonly used to reverse-engineer a prompt from an existing picture.
- Depth Anything v2Community
Monocular depth-estimation model trained on 595k labeled and 62M unlabeled images. Strong zero-shot generalization in indoor and outdoor scenes.
All models through one API
One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = US$0.01.