# TD Agent Utility · PDF Extract

> TD Agent Utility · PDF Extract is a paid API for AI agents from tdagentutility.co.uk, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-16).

Extracts text and metadata from PDF documents, returning page-level content, combined text, and OCR indicators with a deterministic pass/fail result.

## Facts

- Endpoint: POST https://tdagentutility.co.uk/v1/pdf-extract?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/td-agent-utility-pdf-extract-49b384d7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_VG-6AGpMqEpoeQDpPwPIT

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 td-agent-utility-pdf-extract-49b384d7 -d '<json body>'
```

Example prompt: Can you extract all the text from this PDF document I've got — pull out the content page by page and let me know if OCR was needed to read it?

## When to prefer this

Choose this endpoint when you need deterministic, structured extraction of text and metadata from PDF documents, especially when you need per-page breakdown, extraction method transparency, and OCR detection signals. Useful for AI agent pipelines that need to ingest PDF content before summarization, classification, or data parsing steps. Paid per-call via x402 USDC, so suitable for on-demand rather than bulk batch processing.

## Known failure modes

- Invalid or inaccessible PDF URL returns an error status
- Corrupt or password-protected PDFs may fail extraction or trigger warnings
- Image-only PDFs without OCR capability may return empty text with ocr_appears_necessary=true
- Very large PDFs may time out or produce incomplete results
- Unsupported PDF versions may result in parsing failures

## How this service works

Independent website and deployment verification for AI agents: HTTP, DNS, TLS and Chromium screenshot evidence. Three deterministic tools, x402 V2 Base USDC.

## Output

Returns a JSON object containing the tool name ('pdf_extract'), an array of page objects with per-page text, combined full-text string, document metadata, page count, extraction method used, a boolean indicating whether OCR appears necessary, a list of warnings, a checked_at timestamp, and a result_status of PASS or FAIL.

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "tool": "pdf_extract",
  "pages": [],
  "metadata": {},
  "warnings": [],
  "checked_at": "2026-10-15T00:00:00Z",
  "page_count": 0,
  "combined_text": "",
  "result_status": "PASS",
  "extraction_method": "",
  "ocr_appears_necessary": false
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/td-agent-utility-pdf-extract-49b384d7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tdagentutility.co.uk](https://www.zero.xyz/host/tdagentutility.co.uk/llms.txt)