Extract data from PDFs and images
Run OCR on receipts, invoices, and documents—PDF or image—and get clean, structured JSON you can plug straight into your existing workflows.
Reliable field extraction
Convert unstructured receipt and invoice data into clean, structured JSON that your systems can consume.
How extraction works
Three simple steps to convert documents into structured data.
Common extracted fields
Typical fields extracted from receipts and invoices. The exact schema provided with your account should be treated as the source of truth.
The response follows a stable JSON schema for receipts and invoices. Contact us if you'd like the full schema definition.
API endpoint
Use the parse endpoint to get structured data from your documents.
Input: Image file (JPEG, PNG). Convert PDFs to images first.
Output: JSON with extracted fields
Use case: Convert documents to structured data