# delx.ai Page Extract

> delx.ai Page Extract is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Fetches a URL and returns clean page metadata plus readable extracted text, ready for search, routing, or summarization.

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/page-extract
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/api-delx-ai-f9508f55
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_m28aPiyAlwGUY20ypEWpU

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 api-delx-ai-f9508f55 -d '<json body>'
```

Example prompt: Can you pull the clean readable text and page metadata from this URL — https://example.com/article/some-blog-post — so I can summarize it?

## When to prefer this

Choose this endpoint when you need clean, readable text and metadata from a single URL without building your own scraping pipeline. Ideal for AI agents that need to summarize, classify, or route content from arbitrary web pages. Prefer over raw HTTP fetch when you need boilerplate-stripped readable content rather than raw HTML.

## Known failure modes

- URL is unreachable or returns a non-200 status — extraction fails with an error
- Page is JavaScript-rendered and server-side content is minimal — returned text may be sparse
- Paywalled or login-gated page — only publicly visible content is extracted
- Malformed or non-HTTP URL provided — validation error returned
- Rate limit or payment issue — 402 or 429 error returned

## How this service works

Page extract for agents at $0.01 USDC. Call when one public URL needs clean title, host, and bounded main text for routing, RAG prep, or summarization—not general web search and not a multi-URL crawl. Returns structured page metadata and readable content via x402.

## Output

Returns cleaned page metadata (title, description, canonical URL) and extracted readable body text stripped of navigation, ads, and boilerplate, suitable for summarization, search indexing, or routing pipelines.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "HTTP or HTTPS URL to fetch"
  },
  "timeout": {
   "type": "integer",
   "maximum": 15,
   "minimum": 1
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "result": {
   "url": "https://example.com",
   "title": "Example Domain",
   "status": 200,
   "headings": [
    "Example Domain"
   ],
   "final_url": "https://example.com/",
   "description": "Illustrative example site for docs and testing.",
   "text_excerpt": "This domain is for use in illustrative examples.",
   "canonical_url": "https://example.com/"
  },
  "tool_name": "util_page_extract"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/api-delx-ai-f9508f55/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.delx.ai](https://www.zero.xyz/host/api.delx.ai/llms.txt)