Turn remittance advice into structured JSON. Payer, payment reference, amount, and the full invoice-by-invoice breakdown with discounts and deductions - typed and ready to apply against your open receivables. Reads PDF, scanned, and emailed remittances.
Send the remittance and a schema. The payment header and each invoice it settles, with the discount taken and the amount deducted, come back typed and ready to match against your open items.
curl -X POST \
https://api-parse.conversiontools.io/v1/extract \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "file=@remittance.pdf" \
-F 'schema={
"payer": "string",
"payment_reference": "string",
"payment_date": "string",
"payment_method": "string",
"currency": "string",
"total_paid": "number",
"invoices_paid": [{
"invoice_number": "string",
"invoice_date": "string",
"gross_amount": "number",
"discount": "number",
"deduction": "number",
"net_paid": "number"
}],
"unapplied_amount": "number"
}'{
"status": "completed",
"pages": 1,
"data": {
"payer": "Larkspur Retail Group",
"payment_reference": "ACH-20260714-8842",
"payment_date": "2026-07-14",
"payment_method": "ACH",
"currency": "USD",
"total_paid": 18412.55,
"invoices_paid": [
{
"invoice_number": "INV-2026-10488",
"invoice_date": "2026-06-02",
"gross_amount": 12400.00,
"discount": 248.00,
"deduction": 0.00,
"net_paid": 12152.00
},
{
"invoice_number": "INV-2026-10517",
"invoice_date": "2026-06-09",
"gross_amount": 6410.55,
"discount": 0.00,
"deduction": 150.00,
"net_paid": 6260.55
}
],
"unapplied_amount": 0.00
}
}One payment can settle forty invoices. Cash application lives or dies on the line-level detail.
Each settled invoice comes back with its own gross amount, discount taken, deduction, and net paid, so a single incoming payment can be split across every open item it clears.
When a customer pays less than the invoice, the gap is captured on that line as a discount or a deduction instead of vanishing into one lump total. Anything left over lands in the unapplied amount rather than going missing.
No two customers format remittance the same way, and it arrives as a PDF attachment, a scan, or a portal printout. Schema-driven extraction reads all of them with OCR applied automatically, with no template per payer.
Yes. Define invoices_paid as an array and every settled invoice comes back as a separate object with its number, date, gross amount, discount, deduction, and net paid - however many the payment covers.
Yes. Discount and deduction are extracted per invoice line, so a short payment shows up where it belongs instead of being buried in the payment total. Summing net_paid against total_paid then tells you immediately whether anything is unaccounted for.
OCR is applied automatically, so scanned, faxed, and photographed remittances read the same as native PDFs. There is no separate pre-processing step to run first.
Yes. Save the schema once and reference it on every extraction. Layouts differ from payer to payer, but the field set you want back does not, so a single saved schema usually covers the whole customer base.
Uploaded documents are deleted automatically within 24 hours. Extracted data is encrypted in transit and at rest and is never used to train models.
The same schema-driven API works across every document type. Define a schema once, extract from thousands of files.
Extract structured JSON from any document with custom schemas.
Parse any PDF into structured JSON, scanned or digital.
Vendor, line items, totals, tax, and dates from invoices.
Store, items, totals, and payment method from receipts.
PO number, vendor, buyer, and SKU-level line items.
Transactions, running balances, and dates for reconciliation.
Box-level data from W-2, 1099, and other tax forms.
Parties, dates, governing law, and key clauses.
Carrier, parties, ports, containers, and cargo.
Credit amounts matched back to the original invoice.
Meter readings, charges, and totals from any provider.
Line items and periods from balance sheets and reports.
Vendor quotes in one shape so you can compare them.
Earnings, deductions, taxes, and year-to-date totals.
Experience, education, and skills from any CV layout.
Fields and MRZ from passports and ID cards.
Rent, term, deposits, and renewal deadlines.
Claim and policy numbers, dates, and claimed amounts.
Packages and SKU-level lines for receiving.
Ordered versus delivered quantities and sign-off.
Free tier covers your first 100 pages a month. No credit card to start.