Turn claim forms, loss reports, and supporting paperwork into structured JSON. Claim and policy numbers, claimant contact details, incident and report dates, itemized damages, and the total claimed - typed and ready for your claims system. Reads faxes, scans, and phone photos.
Send the claim document and a schema. First notice of loss, claimant details, and every damage line come back in the same shape, no matter which carrier designed the form.
curl -X POST \
https://api-parse.conversiontools.io/v1/extract \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "file=@claim.pdf" \
-F 'schema={
"claim_number": "string",
"policy_number": "string",
"claimant": {
"name": "string",
"address": "string",
"phone": "string"
},
"insurer": "string",
"incident_date": "date",
"report_date": "date",
"claim_type": "string",
"description": "string",
"damages": [{
"item": "string",
"description": "string",
"amount": "number"
}],
"total_claimed": "number",
"adjuster": "string",
"status": "string"
}'{
"status": "completed",
"pages": 6,
"data": {
"claim_number": "CLM-2026-081473",
"policy_number": "HO-4471928",
"claimant": {
"name": "Marta Ellison",
"address": "27 Alder Grove, Fairview, IL",
"phone": "+1 217 555 0184"
},
"insurer": "Cedar Ridge Mutual",
"incident_date": "2026-05-14",
"report_date": "2026-05-16",
"claim_type": "Water damage",
"description": "Burst supply line under kitchen sink",
"damages": [
{
"item": "Kitchen flooring",
"description": "Engineered oak, 22 sq m",
"amount": 4180.00
},
{
"item": "Base cabinets",
"description": "Three units, water swollen",
"amount": 1950.00
}
],
"total_claimed": 6130.00,
"adjuster": "D. Whitmore",
"status": "Under review"
}
}Claims arrive from dozens of carriers, each with its own layout. The schema is what makes them comparable.
Every insurer lays out its claim form differently, and a template-based reader breaks the first time a field moves half an inch. You describe the fields you want and the same schema runs across the whole intake pile.
Each damaged item returns as its own object with a description and an amount, so reserving, coverage checks, and adjuster review all work off line-level data instead of a single number.
Intake is rarely a clean PDF. Photographed forms, faxed loss reports, and multi-page scans are read with OCR applied automatically, so the messy half of the queue stops being manual work.
Yes. Extraction is driven by the schema you send, not by a stored template, so property, motor, and liability forms from different carriers all return the same field names. Onboarding a new carrier does not mean building a new configuration.
Yes. Define damages as an array and each entry comes back with its item, description, and amount, so the sum of the lines can be checked against the amount claimed before a file ever reaches an adjuster.
Handwriting is read where it is legible, and OCR is applied automatically to scans, faxes, and photos. Accuracy tracks the quality of the source document, so it is worth keeping a review step on the fields that drive payment.
Yes. Extraction is asynchronous: you submit the document, then poll for the result or take a webhook when it is ready. The typed JSON maps onto a claims record directly, so it drops into an intake queue with no parsing layer in between.
Uploaded documents are deleted automatically within 24 hours. Extracted data is encrypted in transit and at rest and is never used to train models. Your own retention and handling rules still apply on your side, so review the behaviour against them before sending live claim files.
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.
Payments split across invoices for cash application.
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.
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.