# x402 Agent Hub Web Extractor

> x402 Agent Hub Web Extractor is a paid API for AI agents from x402-agent-hub.x402-agent-hub.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-11-14).

Fetches any public webpage and converts it into clean, token-efficient LLM Markdown with title, meta description, canonical URL, HTTP latency, and token count.

## Facts

- Endpoint: POST https://x402-agent-hub.x402-agent-hub.workers.dev/v1/web/extract?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/x402-agent-hub-web-extractor-fb723783
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_NlG7GQDUheHw_V4GkkhaU

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 x402-agent-hub-web-extractor-fb723783 -d '<json body>'
```

Example prompt: Can you fetch the content of https://openai.com/research/gpt-4 and convert it into clean markdown — limit it to 10000 characters so it's easy to read?

## When to prefer this

Use this endpoint when you need to read, summarize, or process the content of any public webpage in a token-efficient, LLM-ready format. It is ideal when you want clean prose markdown rather than raw HTML, and when you need metadata like page title and word count alongside the content. Prefer this over raw HTTP fetch when token efficiency and clean formatting matter.

## Known failure modes

- Non-public or paywalled URLs return no content or partial content
- Pages requiring JavaScript rendering may return incomplete markdown
- maxChars outside 500–50000 range may cause validation errors
- Unreachable URLs return non-200 HTTP status codes
- Dynamic or login-gated pages may return empty or redirect content

## How this service works

Fetches any public webpage and converts it into clean, token-efficient LLM Markdown alongside title, meta description, canonical URL, HTTP latency, and estimated token count.

## Output

Returns a JSON object containing the original URL, page title, the full page content rendered as clean LLM-friendly Markdown, word count, and the HTTP status code of the fetched page. Content is capped at the requested maxChars limit (between 500 and 50,000 characters).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public http/https URL to extract"
  },
  "maxChars": {
   "type": "number",
   "description": "Maximum Markdown characters to return (500-50000)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/",
  "title": "Example Domain",
  "markdown": "# Example Domain\nThis domain is for use in illustrative examples...",
  "wordCount": 42,
  "httpStatus": 200
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x402-agent-hub-web-extractor-fb723783/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-agent-hub.x402-agent-hub.workers.dev](https://www.zero.xyz/host/x402-agent-hub.x402-agent-hub.workers.dev/llms.txt)
