# page-extract · x402 Supply

> page-extract · x402 Supply is a paid API for AI agents from page-extract.x402supply.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-31).

Fetches a URL and returns clean article text or markdown plus metadata from static HTML pages, with no JavaScript rendering.

## Facts

- Endpoint: POST https://page-extract.x402supply.com/mcp?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-31
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/page-extract-x402-supply-ad40fd58
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Uqfy1DdFTvcmelHyCQt8K

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 page-extract-x402-supply-ad40fd58 -d '<json body>'
```

Example prompt: Can you fetch the article at https://example.com/some-article and give me the clean readable text or markdown — just the main content, no ads or navigation junk?

## When to prefer this

Choose this endpoint when you need to extract clean readable text or markdown from a publicly accessible static HTML page — such as articles, blog posts, or documentation — without needing JavaScript rendering. It is ideal for RAG pipelines, summarization, or any workflow where boilerplate-free article content is needed cheaply at $0.01 per call. If the target page is a JavaScript-heavy SPA or requires authentication, prefer a headless-browser-based scraping service instead.

## Known failure modes

- URL is unreachable or returns a non-200 status code
- Page requires JavaScript rendering to display content (JS-only SPAs will return empty or minimal content)
- URL points to a binary file (PDF, image) rather than HTML
- Anti-bot measures or paywalls block the fetch
- Malformed or extremely large HTML may cause parsing failures

## How this service works

Fetches a URL and returns clean article text/markdown plus metadata. Deterministic, static HTML only, no JS rendering.

## Output

Returns the clean article text or markdown extracted from the page's static HTML, along with page metadata such as title, author, description, and publication date. Content is stripped of navigation, ads, and boilerplate. No JavaScript-rendered content is included.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "toolName",
    "inputSchema"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "mcp"
    },
    "toolName": {
     "type": "string"
    },
    "transport": {
     "enum": [
      "streamable-http"
     ],
     "type": "string"
    },
    "description": {
     "type": "string"
    },
    "inputSchema": {
     "type": "object"
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/page-extract-x402-supply-ad40fd58/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from page-extract.x402supply.com](https://www.zero.xyz/host/page-extract.x402supply.com/llms.txt)