Menu OCR API
Turn restaurant menu photos and PDFs into dishes, descriptions, prices and sections for delivery apps and listings.
結果
変換されたMarkdownやJSONがここに表示されます。
What makes menus hard to read
- Decorative fonts and multi-column layouts
- Prices that sit far from the dish name
- Menus in several languages at once
What you can pull out
menu fields
{
"restaurant": "Trattoria Lucia",
"sections[]": "name, items[]",
"item_name": "Tagliatelle al ragù",
"description": "Slow-cooked beef and pork ragù",
"price": "24.00",
"currency": "EUR",
"dietary_tags": "vegetarian, gluten-free"
}Best models for menus
1Gemini FlashGeneral vision model with strong handwriting and layout understanding at a low price.
google/gemini-flash3 credits / page2GPTGeneral vision model. Good at messy scans and following extraction instructions.openai/gpt11 credits / page3ClaudeGeneral vision model with careful reading of long, dense documents.anthropic/claude14 credits / pageCall it from your code
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-flash",
"file_url": "https://example.com/invoice.pdf",
"format": "json"
}'