Medical record OCR API
Turn scanned medical records, discharge summaries and lab reports into structured patient, diagnosis and medication data.
Result
Your Markdown or JSON shows up here.
What makes medical records hard to read
- Handwritten clinician notes and abbreviations
- Lab tables with units and reference ranges
- Sensitive data that needs careful handling
What you can pull out
medical-record fields
{
"patient_name": "Robert Chen",
"date_of_birth": "1957-09-03",
"record_number": "MRN-0045821",
"visit_date": "2026-10-14",
"diagnoses[]": "code, description",
"medications[]": "name, dose, frequency",
"lab_results[]": "test, value, unit, range",
"physician": "Dr. A. Fischer"
}Best models for medical records
1Gemini FlashGeneral vision model with strong handwriting and layout understanding at a low price.
google/gemini-flash3 credits / page2Azure Document IntelligenceAzure layout model with tables, selection marks and prebuilt invoice and ID readers.azure/document-intelligence15 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"
}'