# PDF Structured Data Extractor (august.services)

> PDF Structured Data Extractor (august.services) is a paid API for AI agents from api-v3qhpbwutp.august.services, paid per call via x402, $0.12/call, status down (last checked 2026-09-15).

Extracts structured JSON from a PDF document (supplied as URL or base64) against a caller-provided JSON Schema, with flat per-document pricing regardless of page count.

## Facts

- Endpoint: POST https://api-v3qhpbwutp.august.services/v1/pdf-extract
- Price: $0.12/call
- Payment: x402
- Status: down
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pdf-structured-data-extractor-august-services-c90b9857
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap__h8Ac8iZQ4R7XHCLQIQKZ

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability pdf-structured-data-extractor-august-services-c90b9857 -d '<json body>'
```

Example prompt: Extract the invoice number, total amount, and due date from this PDF invoice at https://invoices.example.com/INV-2201.pdf — use a JSON Schema with fields invoice_number (string), total (number), and due_date (string).

## When to prefer this

Choose this endpoint when you need to extract structured fields from a text-layer PDF using your own schema definition, especially for multi-page documents where per-page pricing would be costly. Prefer it over generic text extractors when you want JSON output conforming to a specific schema rather than raw text, and over web-scraping endpoints when your source is a PDF rather than an HTML page.

## Known failure modes

- Scanned image-only PDFs (no embedded text layer) are rejected with a clear error rather than returning empty fields
- Invalid or inaccessible PDF URL returns an error
- Malformed JSON Schema input causes a validation error
- PDF that is password-protected or encrypted cannot be read
- Fields in the schema with no matching content in the PDF may be null or absent

## How this service works

Extract structured JSON from a PDF against a JSON Schema you supply. Send a URL or base64 bytes; get back your schema, filled. Whole-document pricing, not per-page: a 20-page contract costs the same as a 2-page invoice. Reads the embedded text layer — scanned image-only PDFs are rejected with a clear error rather than empty fields.

## Output

Returns a JSON object with a 'data' field containing the caller's JSON Schema filled with values extracted from the PDF, plus a 'pages' field indicating how many pages were processed. Fields that could not be found are omitted or null per schema constraints.

## Response schema (JSON Schema)

```json
{
 "example": {
  "data": {
   "total": 4820.5,
   "due_date": "2026-05-01",
   "invoice_number": "INV-2201"
  },
  "pages": 3
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pdf-structured-data-extractor-august-services-c90b9857/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api-v3qhpbwutp.august.services](https://www.zero.xyz/host/api-v3qhpbwutp.august.services/llms.txt)