Form OCR API
Turn filled-in paper and PDF forms into key-value pairs, including checkboxes and handwritten answers.
結果
変換されたMarkdownやJSONがここに表示されます。
What makes forms hard to read
- Handwriting squeezed into small boxes
- Checkbox and radio states
- Matching each answer to the right label
What you can pull out
form fields
{
"applicant_name": "Hannah Weiss",
"date": "2026-10-30",
"checkboxes": "{ \"consent\": true, \"newsletter\": false }",
"signature_present": "true",
"fields": "{ \"phone\": \"+61 412 555 019\", \"postcode\": \"3000\" }"
}Best models for forms
1Azure Document IntelligenceAzure layout model with tables, selection marks and prebuilt invoice and ID readers.
azure/document-intelligence15 credits / page2Amazon TextractAWS OCR with form key-value pairs, tables and per-word confidence scores.aws/textract6 credits / page3Gemini FlashGeneral vision model with strong handwriting and layout understanding at a low price.google/gemini-flash3 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": "azure/document-intelligence",
"file_url": "https://example.com/invoice.pdf",
"format": "json"
}'