Extract structured JSON data from a PDF document

[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "payTo": "0xA0AC44BECC6302298f01ed255B175ca1060C189E",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "20000",
    "maxTimeoutSeconds": 300
  }
]

{
  "bazaar": {
    "info": {
      "input": {
        "body": {
          "file": "invoice.pdf",
          "schema": "[\"invoice_number\",\"date\",\"total\",\"vendor_name\"]"
        },
        "bodyType": "form-data",
        "method": "POST",
        "type": "http"
      },
      "output": {
        "example": {
          "data": {
            "date": "2026-08-01",
            "invoice_number": "INV-2041",
            "total": "£412.00",
            "vendor_name": "Acme Supplies Ltd"
          },
          "meta": {
            "pages": 1,
            "truncated": false
          }
        },
        "type": "json"
      }
    },
    "schema": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "properties": {
        "input": {
          "additionalProperties": false,
          "properties": {
            "body": {
              "properties": {
                "file": {
                  "format": "binary",
                  "type": "string"
                },
                "schema": {
                  "type": "string"
                }
              },
              "required": [
                "file"
              ]
            },
            "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"
    }
  }
}

curl "https://pdf-extract-api.pdfextractapi.workers.dev/extract"
# -> 402 Payment Required, accepts[] lists how to pay
# retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid

const res = await fetch("https://pdf-extract-api.pdfextractapi.workers.dev/extract");
if (res.status === 402) {
  const { accepts } = await res.json();
  // pay one of accepts[] via an x402 client, then retry with the payment header
}

import httpx
res = httpx.get("https://pdf-extract-api.pdfextractapi.workers.dev/extract")
if res.status_code == 402:
    accepts = res.json()["accepts"]
    # pay one of accepts[] via an x402 client, then retry with the payment header