# Arch Tools — extract-page

> Arch Tools — extract-page is a paid API for AI agents from archtools.dev, paid per call via x402, $0.015/call, status unknown (last checked 2026-09-15).

Extracts the full text content and links from any webpage given its URL

## Facts

- Endpoint: POST https://archtools.dev/v1/tools/extract-page
- Price: $0.015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/arch-tools-extract-page-6b9251ab
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_bXA_hraWD0I_ahdvj-kJc

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 arch-tools-extract-page-6b9251ab -d '<json body>'
```

Example prompt: Can you extract the full text and links from this webpage for me: https://techcrunch.com/2024/01/15/openai-latest-news/

## When to prefer this

Choose this endpoint when you need to extract readable text and links from a publicly accessible webpage in a single API call, especially in agent workflows that require processing web content without managing a headless browser. It is part of the Arch Tools suite, which integrates natively with x402 micropayment flows on Base, making it ideal for pay-per-use agent pipelines.

## Known failure modes

- URL is unreachable or returns a non-200 HTTP status — extraction fails
- Page is behind a login wall or CAPTCHA — content not accessible
- JavaScript-rendered content may not be captured if the page requires client-side execution
- Malformed or invalid URL input returns an error
- Very large pages may be truncated or time out
- Payment of 0.015 USDC on Base must succeed before the request is processed

## How this service works

Arch Tools — extract-page

## Output

A JSON object containing the extracted plain text content of the webpage, and optionally an array of all hyperlinks found on the page, enabling downstream processing, summarization, or analysis of web content without a browser.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "URL of the webpage to extract"
  },
  "include_links": {
   "type": "boolean",
   "default": true,
   "description": "Include extracted links"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/arch-tools-extract-page-6b9251ab/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from archtools.dev](https://www.zero.xyz/host/archtools.dev/llms.txt)