# AgentToll Deep Page Extract

> AgentToll Deep Page Extract is a paid API for AI agents from agent-toll.agentfetcher.workers.dev, paid per call via x402, $0.0075/call, status unknown (last checked 2026-09-15).

Extracts structured data from a public URL including headings, meta tags, JSON-LD, emails, phones, and markdown for lead enrichment and agent workflows

## Facts

- Endpoint: GET https://agent-toll.agentfetcher.workers.dev/v1/extract
- Price: $0.0075/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agenttoll-deep-page-extract-6d52db7b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_i26lrvm01685yfMXxepAu

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-deep-page-extract-6d52db7b
```

Example prompt: Pull all the contact info, headings, meta tags, and JSON-LD from https://example-company.com — I need emails, phone numbers, and any structured schema data for lead enrichment.

## When to prefer this

Use this endpoint over the sibling llm-pack endpoint when you need contact information (emails, phones), structured schema data (JSON-LD), or meta tags in addition to readable content. Choose this when enriching leads, building contact lists, or when structured semantic data from the page is required — not just readable markdown.

## Known failure modes

- URL is behind a login or paywall — returns empty or partial data
- Page has no structured JSON-LD or meta tags — those fields return empty
- JavaScript-rendered SPA content may not be fully captured
- Invalid or unreachable URL returns an error response
- Rate limiting or bot protection on target site blocks fetch

## 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 payload containing extracted email addresses, phone numbers, page headings, HTML meta tags, JSON-LD structured data blocks, and a markdown rendering of the page content — all parsed from the target URL.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public URL for deep extract: emails, phones, headings, meta, JSON-LD, markdown"
  },
  "noCache": {
   "type": "boolean",
   "description": "Skip cache and re-fetch the page"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "title": "Example Domain",
  "emails": [],
  "phones": [],
  "headings": [
   "Example Domain"
  ],
  "markdown": "# Example Domain\n\n..."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agenttoll-deep-page-extract-6d52db7b/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)