# VerifyLite Web Page Reader

> VerifyLite Web Page Reader is a paid API for AI agents from verifylite.hydratinghealingtouch.workers.dev, paid per call via x402, $0.0028/call, status unknown (last checked 2026-10-22).

Fetches a URL and returns its main content as clean markdown with title, description, language, and word count, stripping navigation, footers, scripts, and styles

## Facts

- Endpoint: POST https://verifylite.hydratinghealingtouch.workers.dev/read?utm_source=zero.xyz
- Price: $0.0028/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-22
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verifylite-web-page-reader-34246232
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_obA9wIC78pBWuf1rMkHj_

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 verifylite-web-page-reader-34246232 -d '<json body>'
```

Example prompt: Can you fetch the article at https://www.bbc.com/news/technology-12345678 and give me the main text as clean readable markdown so I can summarize it?

## When to prefer this

Use this endpoint when you need clean, LLM-ready markdown extracted from a single webpage without navigation noise — ideal for article summarization, research ingestion, or feeding web content to a language model. Prefer it over raw HTML fetching when you need structured output (title, description, language, word count) alongside the text, and when you want links normalized to absolute form automatically.

## Known failure modes

- URL is unreachable or returns non-200 HTTP status — not charged, error response returned
- URL points to a non-text resource (PDF, image, binary) — not charged
- URL is malformed or not absolute HTTP/HTTPS — validation error
- Page uses heavy JavaScript rendering and content is not in initial HTML — may return empty or partial content
- Page blocks bots via CAPTCHA or Cloudflare challenge — fetch fails, not charged
- Network timeout on slow or unresponsive servers

## How this service works

Web page reader: fetches one URL and returns its main content as clean markdown with the page title, description, language, and word count. Uses the site's own Markdown version when it offers one; otherwise strips navigation, footers, scripts, and styles. Includes a token estimate. Useful for feeding web pages to an LLM, summarizing articles, or extracting text for research. Not charged if the page can't be fetched or isn't text.

## Output

Returns the page's main readable content as clean markdown with all links converted to absolute markdown format, along with the page title, meta description, detected language, and word count. Navigation menus, footers, scripts, and styles are stripped. If the page cannot be fetched or is not text content, the call is not charged.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Absolute HTTP or HTTPS URL of the page to read."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verifylite-web-page-reader-34246232/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from verifylite.hydratinghealingtouch.workers.dev](https://www.zero.xyz/host/verifylite.hydratinghealingtouch.workers.dev/llms.txt)