One API Surface
A single documents endpoint covers invoices and receipts across PDF and image formats.
Document Extraction API
Document extraction that returns application data.
Parseify is a document extraction API for finance workflows: upload an invoice or receipt and get clean JSON fields your product can use immediately — not a blob of OCR text.
Request
curl -X POST https://api.parseify.app/api/v1/documents \ -H "X-Api-Key: bnj_live_xxxxxxxxxxxxxxxxxxxxxx" \ -F "file=@document.pdf"Response
{
"vendor": "Byte Office Supplies",
"invoiceNumber": "INV-2026-0419",
"date": "2026-04-19",
"totalAmount": 499.13,
"vatAmount": 86.63,
"currency": "EUR",
"lineItems": [
{ "description": "A4 paper box", "quantity": 3, "unitPrice": 29.90, "totalPrice": 89.70 }
]
} Document intelligence for product teams
Stable Schema
Field names stay consistent so you can version your integration and validate responses with confidence.
Usage-Based Plans
Start free, then scale with Growth or Pro as document volume grows — see billing for current limits.
Document extraction API, frequently asked questions
What is a document extraction API?
A document extraction API reads PDFs and images and returns structured data. Parseify focuses on invoices and receipts, extracting vendor, dates, amounts, and line items as JSON.
How does Parseify's document extraction API work?
You upload a file to /api/v1/documents with an API key. The service returns schema-stable JSON your application can store and process without building OCR infrastructure.
Which document types are supported?
Invoices and receipts as PDF, PNG, or JPEG up to 20 MB. All inputs share one response schema so downstream code stays simple.
Is document extraction the same as keyword search in a PDF?
No. Document extraction understands business fields — totals, tax, vendors, line items — and returns them as named JSON properties rather than searchable plain text.