Prompt

invoice OCR structured JSON

Artificial Intelligence / Computer Vision1 observationLast seen Oct 2, 2026

Latest observation

Oct 2, 2026OpenAI APIWeb search: off

Here’s a practical structured JSON schema for invoice OCR output. You can use it as a target format for an OCR/parsing pipeline.

{
  "document_type": "invoice",
  "confidence": 0.0,
  "source_file": "",
  "language": "",
  "page_count": 0,
  "invoice": {
    "invoice_number": "",
    "invoice_date": "",
    "due_date": "",
    "purchase_order_number": "",
    "currency": "",
    "payment_terms": "",
    "status": ""
  },
  "seller": {
    "name": "",
    "tax_id": "",
    "vat_id": "",
    "address": {
      "line1": "",
      "line2": "",
      "city": "",
      "state": "",
      "postal_code": "",
      "country": ""
    },
    "phone": "",
    "email": "",
    "website": ""
  },
  "buyer": {
    "name": "",
    "tax_id": "",
    "vat_id": "",
    "address": {
      "line1": "",
      "line2": "",
      "city": "",
      "state": "",
      "postal_code": "",
      "country": ""
    }
  },
  "shipping": {
    "name": "",
    "address": {
      "line1": "",
      "line2": "",
      "city": "",
      "state": "",
      "postal_code": "",
      "country": ""
    },
    "method": "",
    "tracking_number": ""
  },
  "line_items": [
    {
      "line_number": 1,
      "description": "",
      "quantity": 0,
      "unit_of_measure": "",
      "unit_price": 0.0,
      "discount": 0.0,
      "tax_rate": 0.0,
      "tax_amount": 0.0,
      "line_total": 0.0
    }
  ],
  "summary": {
    "subtotal": 0.0,
    "discount_total": 0.0,
    "tax_total": 0.0,
    "shipping_total": 0.0,
    "other_charges": 0.0,
    "grand_total": 0.0,
    "amount_paid": 0.0,
    "amount_due": 0.0
  },
  "payment": {
    "method": "",
    "bank_name": "",
    "account_name": "",
    "account_number": "",
    "iban": "",
    "swift_bic": "",
    "reference": ""
  },
  "metadata": {
    "ocr_engine": "",
    "parse_version": "",
    "extraction_timestamp": "",
    "warnings": []
  }
}

Example filled JSON

{
  "document_type": "invoice",
  "confidence": 0.98,
  "source_file": "invoice_001.pdf",
  "language": "en",
  "page_count": 1,
  "invoice": {
    "invoice_number": "INV-10482",
    "invoice_date": "2026-01-15",
    "due_date": "2026-02-14",
    "purchase_order_number": "PO-77821",
    "currency": "USD",
    "payment_terms": "Net 30",
    "status": "unpaid"
  },
  "seller": {
    "name": "Acme Supplies Inc.",
    "tax_id": "12-3456789",
    "vat_id": "",
    "address": {
      "line1": "100 Market Street",
      "line2": "Suite 500",
      "city": "San Francisco",
      "state": "CA",
      "postal_code": "94105",
      "country": "US"
    },
    "phone": "+1-415-555-0100",
    "email": "billing@acme.com",
    "website": "https://acme.com"
  },
  "buyer": {
    "name": "Globex Corporation",
    "tax_id": "",
    "vat_id": "",
    "address": {
      "line1": "250 Park Avenue",
      "line2": "",
      "city": "New York",
      "state": "NY",
      "postal_code": "10177",
      "country": "US"
    }
  },
  "shipping": {
    "name": "Globex Corporation Warehouse",
    "address": {
      "line1": "88 Warehouse Road",
      "line2": "",
      "city": "Jersey City",
      "state": "NJ",
      "postal_code": "07305",
      "country": "US"
    },
    "method": "Ground",
    "tracking_number": "1Z999AA10123456784"
  },
  "line_items": [
    {
      "line_number": 1,
      "description": "Printer Paper A4",
      "quantity": 10,
      "unit_of_measure": "box",
      "unit_price": 12.5,
      "discount": 0.0,
      "tax_rate": 8.25,
      "tax_amount": 10.31,
      "line_total": 135.31
    }
  ],
  "summary": {
    "subtotal": 125.0,
    "discount_total": 0.0,
    "tax_total": 10.31,
    "shipping_total": 0.0,
    "other_charges": 0.0,
    "grand_total": 135.31,
    "amount_paid": 0.0,
    "amount_due": 135.31
  },
  "payment": {
    "method": "ACH",
    "bank_name": "First National Bank",
    "account_name": "Acme Supplies Inc.",
    "account_number": "****1234",
    "iban": "",
    "swift_bic": "",
    "reference": "INV-10482"
  },
  "metadata": {
    "ocr_engine": "example-ocr-v1",
    "parse_version": "1.0",
    "extraction_timestamp": "2026-01-15T10:30:00Z",
    "warnings": []
  }
}

If you want, I can also provide:

  1. a minimal JSON schema
  2. a JSON Schema (draft 2020-12) for validation
  3. a Python/Pydantic model
  4. a multi-invoice OCR output format

Observation history

How did Obsurfable measure this prompt?

Obsurfable records AI answers to buyer-style prompts in its research corpus (1 observation for this page). Metrics are distributions over observations, not a single static ranking.

Which AI systems does Obsurfable collect answers from?

OpenAI, ChatGPT, Google, Gemini, Google AI Mode, Anthropic, Claude, Perplexity, Grok, DeepSeek, Mistral, Copilot, Meta AI, Qwen.

How can brands improve their AEO?

Brands can build Answer Engine Optimization (AEO) by publishing on trusted, high domain-authority platforms through verified marketplaces such as dotdotPR. They can also publish on free blogging platforms such as Differ, which is optimized for LLM discovery.

Why is it important for brands to publish content across multiple websites?

Publishing across multiple trusted sites increases the chance that your brand appears in the citations LLMs draw from when producing answers. Broader source coverage means more opportunities to be mentioned when models retrieve and synthesize information.

Want this interpreted for your brand?

Explorer is the free public corpus. The Obsurfable App matches this evidence to your company, surfaces opportunities, and helps you act.