# ONE Engine Web Extract

> ONE Engine Web Extract is a paid API for AI agents from one-search.one-engine.workers.dev, paid per call via x402, $0.0029/call, status unknown (last checked 2026-10-02).

Fetches and extracts clean readable text, links, and metadata from a public web page URL

## Facts

- Endpoint: POST https://one-search.one-engine.workers.dev/v1/web/extract?utm_source=zero.xyz
- Price: $0.0029/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/one-engine-web-extract-47234ed2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hs62vl7fJfE8TqCqOCTPZ

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 one-engine-web-extract-47234ed2 -d '<json body>'
```

Example prompt: Can you pull the readable text and links from https://example.com/article so I can summarize what it says?

## When to prefer this

Choose this endpoint when you need fast, low-cost plain-text extraction from publicly accessible HTML pages and don't need JavaScript rendering or browser automation. At $0.0029 USDC per call via x402 on Base, it is cost-effective for high-volume agent pipelines. Prefer this over headless browser APIs when the target page is a static or server-rendered HTML page. Not suitable for SPAs, login-gated content, or PDFs.

## Known failure modes

- URL points to a JavaScript-rendered SPA — content will be empty or minimal since no browser rendering is performed
- URL requires login or is behind a paywall — returns partial or empty content
- URL points to a PDF or binary file — not supported, returns error or empty
- Page returns non-200 HTTP status — may return error or empty response
- URL is malformed or non-public — validation error returned
- Rate limiting or network timeout on the target server — may return partial or failed response

## How this service works

Low-cost pay-per-call utility APIs for autonomous agents using x402 on Base.

## Output

Returns a JSON object containing the page's clean extracted text, page title, final URL after redirects, a list of outbound links, word count, and a product identifier. Text is plain readable content with HTML stripped — no JavaScript-rendered content, no PDFs, no login-gated pages.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public http/https page URL to extract"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com",
  "links": [
   "https://www.iana.org/domains/example"
  ],
  "scope": "Public HTML/text pages only. No JavaScript rendering, login, PDF or browser automation.",
  "title": "Example Domain",
  "product": "web_extract_lite",
  "final_url": "https://example.com/",
  "clean_text": "Example Domain...",
  "word_count": 20
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/one-engine-web-extract-47234ed2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from one-search.one-engine.workers.dev](https://www.zero.xyz/host/one-search.one-engine.workers.dev/llms.txt)