# TD Agent Utility · PDF Table Extraction

> TD Agent Utility · PDF Table Extraction is a paid API for AI agents from tdagentutility.co.uk, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-16).

Extracts tabular data from PDF documents and returns structured table data with metadata about the extraction method and page count.

## Facts

- Endpoint: POST https://tdagentutility.co.uk/v1/pdf-tables?utm_source=zero.xyz
- Price: $0.01/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-table-extraction-e77d2564
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_OrTeHwbE75UZOi_IJc7Oc

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-table-extraction-e77d2564 -d '<json body>'
```

Example prompt: Can you extract all the tables from this PDF and give me the data in structured form? Here's the file: https://example.com/annual-report-2024.pdf

## When to prefer this

Use this endpoint when you need to extract structured tabular data from a PDF document and need a deterministic, verifiable result with metadata about how the extraction was performed. Prefer it over generic OCR tools when the PDF has a text layer and you specifically need table structure preserved. At $0.01 per call it is cost-effective for single-document extraction tasks within agent workflows.

## Known failure modes

- PDF URL inaccessible or returns non-200 status — tables array empty with warning
- Scanned/image-only PDF with no text layer — no tables extractable, warning returned
- Malformed or encrypted PDF — extraction fails with error status
- PDF with no tabular content — empty tables array with PASS status and warning
- Very large PDFs may time out or return partial results

## 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

A JSON object containing: the tool name ('pdf_tables'), an array of extracted tables (each with their rows and columns), any warnings encountered during extraction, the timestamp of extraction (checked_at), total page count of the PDF, a result_status ('PASS' or similar), and the extraction_method used.

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "tool": "pdf_tables",
  "tables": [],
  "warnings": [],
  "checked_at": "2026-10-15T00:00:00Z",
  "page_count": 0,
  "result_status": "PASS",
  "extraction_method": ""
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/td-agent-utility-pdf-table-extraction-e77d2564/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)