# x402-farm Web Extractor

> x402-farm Web Extractor is a paid API for AI agents from x402-farm.vercel.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-13).

Fetches a URL and returns its title and full content as Markdown, billed per-call via USDC on Base using the x402 protocol.

## Facts

- Endpoint: GET https://x402-farm.vercel.app/v1/extract
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/x402-farm-web-extractor-4f29357f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_7mo5OOdhzBAFkbNkeByHl

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 x402-farm-web-extractor-4f29357f
```

Example prompt: Fetch the page at https://openai.com/blog and give me the full text content as Markdown so I can summarize it.

## When to prefer this

Choose this endpoint when you need a pay-as-you-go, no-account-required way to fetch and Markdown-ify arbitrary web pages inside an AI agent workflow, especially when you want on-chain micropayment billing via USDC on Base rather than managing API keys or subscriptions.

## Known failure modes

- Non-existent or unreachable URL returns an error or empty content
- Pages behind authentication or paywalls may return login page content rather than the actual article
- JavaScript-heavy single-page apps may return empty or minimal Markdown if JS is not executed
- Payment failure (insufficient USDC balance or x402 protocol error) blocks the request entirely
- Rate limits or bot-detection on the target site may cause fetch failures

## How this service works

Pay-per-call APIs for AI agents — x402 protocol, USDC on Base, no account needed.

## Output

A JSON object containing the canonical URL of the fetched page, its HTML title, and the full page body converted to Markdown text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "properties": {}
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/",
  "title": "Example Domain",
  "markdown": "# Example Domain…"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x402-farm-web-extractor-4f29357f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-farm.vercel.app](https://www.zero.xyz/host/x402-farm.vercel.app/llms.txt)