# AgentToll Clean — Single URL Web Page Cleaner

> AgentToll Clean — Single URL Web Page Cleaner is a paid API for AI agents from agent-toll.agentfetcher.workers.dev, paid per call via x402, $0.0015/call, status unknown (last checked 2026-09-14).

Fetches a public webpage and returns structured JSON with title, plain text, markdown, and extracted links — stripped of HTML chrome, no browser required.

## Facts

- Endpoint: GET https://agent-toll.agentfetcher.workers.dev/v1/clean
- Price: $0.0015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agenttoll-clean-single-url-web-page-cleaner-1004644e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_6FXhMQzsJPqq3gxNSZc18

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 agenttoll-clean-single-url-web-page-cleaner-1004644e
```

Example prompt: Can you fetch and clean the content of https://example.com/article so I get the title, plain text, and all links back as structured JSON — and skip any cached version?

## When to prefer this

Use this endpoint when you need to quickly and cheaply convert a single public webpage into structured, LLM-ready content (title, text, markdown, links) without spinning up a browser. It is ideal for bulk triage across many URLs before committing to deeper, more expensive extraction packs. Prefer this over the multi-URL pack when processing one URL at a time or when cost per call is a priority.

## Known failure modes

- URL is not publicly accessible or returns non-200 — endpoint may return an error or empty content
- Payment of exactly $0.002 USDC on Base not provided or fails — request rejected via x402 payment error
- URL points to a non-HTML resource (PDF, image, binary) — text extraction may be empty or malformed
- Page is heavily JavaScript-rendered — since no browser is used, dynamic content may not appear
- Cache miss with noCache:true on a slow page — increased latency

## How this service works

Free paywall co-pilot /v1/resolve. Paid llm-pack $0.005, clean $0.002, extract $0.01. x402 USDC on Base. No free trial. No hub.

## Output

Returns a structured JSON object containing the page title, extracted plain text, markdown-formatted body content, and a list of links found on the page. Suitable for direct consumption by LLMs or downstream agent pipelines.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public webpage URL to clean into agent-ready JSON (title, text, markdown, links)"
  },
  "noCache": {
   "type": "boolean",
   "description": "Skip cache and re-fetch the page"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "Example Domain...",
  "links": [
   {
    "href": "https://iana.org/domains/example",
    "text": "Learn more"
   }
  ],
  "title": "Example Domain",
  "markdown": "# Example Domain\n\n...",
  "wordCount": 21
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agenttoll-clean-single-url-web-page-cleaner-1004644e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-toll.agentfetcher.workers.dev](https://www.zero.xyz/host/agent-toll.agentfetcher.workers.dev/llms.txt)