SchemaLock — extract structured JSON data from an invoice PDF or image (vendor, line items
SchemaLock — extract structured JSON data from an invoice PDF or image (vendor, line items, subtotal, tax, total, dates, payment terms). Unlike generic OCR (raw text) or text-only extraction APIs, this takes the raw file directly and validates against source math: line items checked against subtotal/tax/total, dates and currency checked, one automatic retry. If it still fails after that, you aren't charged — settlement is skipped, not just flagged.
20000 (raw units)
price
4
calls / 30d
2
unique payers
2026-09-08
updated
Provider
doc-extract-api.thestarboy9696-4ef.workers.dev · discovered, not yet claimed by its owner
Payment (x402 accepts[])
[
{
"scheme": "exact",
"network": "eip155:8453",
"payTo": "0x65c767C483dd862d08Bc3d6500Cd4CD770Ae28ED",
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"amount": "20000",
"maxTimeoutSeconds": 300
}
]Output schema
{
"bazaar": {
"info": {
"input": {
"body": {
"file": "<binary: PDF, PNG, or JPEG of an invoice, max 15MB>"
},
"bodyType": "form-data",
"method": "POST",
"type": "http"
},
"output": {
"example": {
"data": {
"bill_to": {
"address": "55 Market St, Austin, TX 78701",
"name": "Brandon Strouse"
},
"confidence": {
"fields": {
"total": 0.99,
"vendor": 0.99
},
"overall": 0.97
},
"currency": "USD",
"due_date": "2026-08-31",
"invoice_date": "2026-08-01",
"invoice_number": "INV-20268",
"line_items": [
{
"amount": 45,
"description": "Widget A (steel)",
"quantity": 10,
"unit_price": 4.5
},
{
"amount": 30,
"description": "Widget B (plastic)",
"quantity": 25,
"unit_price": 1.2
},
{
"amount": 18,
"description": "Shipping crate",
"quantity": 1,
"unit_price": 18
}
],
"payment_terms": "Net 30",
"subtotal": 93,
"tax": 7.44,
"total": 100.44,
"vendor": {
"address": "123 Industrial Ave, Springfield, IL 62701",
"name": "Acme Supply Co.",
"tax_id": "12-3456789"
}
},
"retried": false,
"validation_warnings": []
},
"type": "json"
}
},
"schema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"body": {
"properties": {}
},
"bodyType": {
"enum": [
"json",
"form-data",
"text"
],
"type": "string"
},
"method": {
"enum": [
"POST"
],
"type": "string"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method",
"bodyType",
"body"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}
}
}Use it
curl
curl "https://doc-extract-api.thestarboy9696-4ef.workers.dev/extract/invoice" # -> 402 Payment Required, accepts[] lists how to pay # retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid
JavaScript
const res = await fetch("https://doc-extract-api.thestarboy9696-4ef.workers.dev/extract/invoice");
if (res.status === 402) {
const { accepts } = await res.json();
// pay one of accepts[] via an x402 client, then retry with the payment header
}Python
import httpx
res = httpx.get("https://doc-extract-api.thestarboy9696-4ef.workers.dev/extract/invoice")
if res.status_code == 402:
accepts = res.json()["accepts"]
# pay one of accepts[] via an x402 client, then retry with the payment headerMachine-readable
Everything on this page is also available as clean JSON at /resources/8242.json, and this resource appears in /discovery/resources and /discovery/search.