Extract structured data from invoice or receipt text — or directly from an invoi

Extract structured data from invoice or receipt text — or directly from an invoice URL (PDF, HTML, or plain text, fetched and parsed server-side) — using Claude Haiku: returns vendor, invoice number, dates, line items, subtotal, tax, total, and currency as clean JSON for accounts-payable, expense processing, and bookkeeping automation.

Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.

Endpoint

POST https://netintel.dev/extract/invoice

Our checks, last 30 days

Example input (from the provider)

{
  "body": {
    "text": "Acme Supplies Inc\nInvoice INV-2024-0142\nDate: 2024-03-01  Due: 2024-03-31\nWidget A  10 x $5.00 = $50.00\nShipping  1 x $12.00 = $12.00\nSubtotal: $62.00\nTax: $5.58\nTotal: $67.58 USD"
  },
  "bodyType": "json",
  "method": "POST",
  "type": "http"
}

Promised output schema (from the provider)

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "input": {
      "additionalProperties": false,
      "properties": {
        "body": {
          "properties": {
            "text": {
              "description": "The invoice or receipt content ITSELF (email body, OCR dump, pasted PDF text) \u2014 not an instruction or question about an invoice. Have only a link? Pass url instead. Text with no extractable invoice data returns an uncharged 400 (NO_INVOICE_CONTENT). Max 10000 words or 50KB.",
              "type": "string"
            },
            "url": {
              "description": "Publicly reachable invoice URL \u2014 PDF, HTML, or plain text; fetched and parsed server-side (e.g. https://vendor.example/invoice-42.pdf). Provide exactly one of text or url.",
              "type": "string"
            }
          },
          "type": "object"
        },
        "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": {
          "properties": {
            "cached": {
              "description": "True if served from the in-memory cache.",
              "type": "boolean"
            },
            "findings": {
              "description": "Informational findings (e.g. no_total_found, totals_mismatch).",
              "items": {
                "type": "string"
              },
              "type": "array"
            },
            "grade": {
              "description": "Letter grade A-F",
              "type": "string"
            },
            "invoice": {
              "description": "Parsed invoice fields: vendor, invoice_number, invoice_date, due_date, line_items (array of {description, quantity, unit_price, amount}), subtotal, tax, total, currency. Missing fields are null.",
              "type": "object"
            },
            "line_item_count": {
              "description": "Number of line items extracted.",
              "type": "number"
            },
            "score": {
              "description": "Quality score 0-100",
              "type": "number"
            },
            "source": {
              "description": "Where the invoice content came from. type is \"text\" or \"url\"; url and content_type (pdf | html | text) are null in text mode.",
              "properties": {
                "content_type": {
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "type": {
                  "type": "string"
                },
                "url": {
                  "type": [
                    "string",
                    "null"
                  ]
                }
              },
              "type": "object"
            },
            "totals_reconcile": {
              "description": "True if sum(line_items.amount) + tax \u2248 total (within $0.02). False if they do not reconcile. Null if total or subtotal is missing.",
              "type": [
                "boolean",
                "null"
              ]
            }
          },
          "type": "object"
        },
        "type": {
          "type": "string"
        }
      },
      "required": [
        "type"
      ],
      "type": "object"
    }
  },
  "required": [
    "input"
  ],
  "type": "object"
}

This page as JSON