# TD Agent Utility · Read Page (Website Content Extraction)

> TD Agent Utility · Read Page (Website Content Extraction) is a paid API for AI agents from tdagentutility.co.uk, paid per call via x402, $0.008/call, status unknown (last checked 2026-10-16).

Fetches and extracts the full content of a web page — including title, headings, main text, links, and markdown — using HTTP or a headless Chromium browser.

## Facts

- Endpoint: POST https://tdagentutility.co.uk/v1/read-page?utm_source=zero.xyz
- Price: $0.008/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-read-page-website-content-extraction-94b23660
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_tpNcPa4FsSS0V1khTxsL2

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-read-page-website-content-extraction-94b23660 -d '<json body>'
```

Example prompt: Can you fetch the content of https://example.com and give me the main text, title, and all the links — use a real browser to render it properly?

## When to prefer this

Choose this endpoint when you need to read the actual rendered or raw content of a specific URL — including title, headings, links, and markdown — especially when you need evidence of what a live deployment is showing. It is particularly useful when you need Chromium-rendered content (JavaScript-heavy SPAs) rather than just raw HTML. Prefer it over general search APIs when you already know the URL and need the page's full textual content.

## Known failure modes

- URL is unreachable or returns a non-2xx HTTP status — result_status will be FAIL with http_status populated
- Chromium rendering times out for JavaScript-heavy pages — may fall back to HTTP extraction with warnings
- DNS resolution failure for the target domain — returns error in warnings
- Redirects exceed limit — final_url will differ from requested_url
- Paywalled or bot-blocked pages may return empty or partial content

## 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, result_status (PASS/FAIL), HTTP status code, page title, headings array, main_text, markdown, links, final_url, canonical_url, meta_description, content_type, bytes_read, browser_used flag, extraction_method, timing_seconds, checked_at timestamp, and any warnings.

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "tool": "read_page",
  "links": [],
  "title": "",
  "headings": [],
  "markdown": "",
  "warnings": [],
  "final_url": "",
  "main_text": "",
  "bytes_read": 0,
  "checked_at": "2026-10-15T00:00:00Z",
  "http_status": 0,
  "browser_used": false,
  "content_type": "",
  "canonical_url": null,
  "requested_url": "",
  "result_status": "PASS",
  "timing_seconds": 0,
  "meta_description": "",
  "extraction_method": ""
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/td-agent-utility-read-page-website-content-extraction-94b23660/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)