OCRRouterGet API key

GPT vs Donut

Donut is cheaper per page; Donut is faster; only GPT supports tables, handwriting, math, multilingual; only Donut supports forms.

GPTopenai/gptDonutnaver/donut
TypeVision modelOpen source
Price11 credits / page1 credits / page
Per 1,000 pages$11.00$1.00
Typical speed2.4 s / page1.0 s / page
Best forMessy scans, custom instructionsReceipt and form fields after fine-tuning
InputsPDF, imagesimages
Languages50+ languagesEnglish, Chinese, Japanese, Korean
Max pages per request100100
Tables✓ YesNo
Handwriting✓ YesNo
Math✓ YesNo
Bounding boxesNoNo
ConfidenceNoNo
FormsNo✓ Yes
Multilingual✓ YesNo
On OCRRouterAvailableComing soon

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

What each one is

GPT

General vision model. Good at messy scans and following extraction instructions.

GPT details

Donut

OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.

Donut details

Use one, fall back to the other

Request body
{
  "model": "openai/gpt",
  "fallbacks": ["naver/donut"],
  "file_url": "https://example.com/document.pdf"
}

Questions

More comparisons

GPT alternativesDonut alternatives