KYC OCR
Read passports, ID cards, driver's licenses and proof-of-address letters in one KYC flow, and get the identity fields back in one shape whatever the document.
PDF, PNG, JPG, WebP, HEIC. Up to 10 files at onceNo file?
What makes KYC documents hard to read
- Hundreds of ID layouts across countries and states
- Phone photos with glare, blur and cropped edges
- Name order and transliteration that differ between documents
Fields coming with document_type
{"document_type": "passport","issuing_country": "GBR","document_number": "533380006","full_name": "AMELIA JANE HUGHES","date_of_birth": "1991-03-08","expiry_date": "2030-09-14","address": "41 Kelvin Rd, Glasgow G12 8QQ","mrz_valid": "true"}Best models for KYC documents
1Azure Document IntelligenceAzure layout model with tables, selection marks and prebuilt invoice and ID readers.60 credits / page
azure/document-intelligence60 credits / page2Gemini FlashGeneral vision model with strong handwriting and layout understanding at a low price.15 credits / pagegoogle/gemini-flash15 credits / page3Amazon TextractAWS OCR with form key-value pairs, tables and per-word confidence scores.25 credits / pageaws/textract25 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"
}'