# Agent Data API — Web Extract

> Agent Data API — Web Extract is a paid API for AI agents from 168.231.82.195.sslip.io, paid per call via x402, $0.01/call, status down (last checked 2026-09-15).

Fetches a URL and returns clean, readable extracted text content from the page

## Facts

- Endpoint: GET https://168.231.82.195.sslip.io/extract
- Price: $0.01/call
- Payment: x402
- Status: down
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-data-api-web-extract-db58f715
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Yz_yqGkpQTQ-UbBlJAfoF

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 agent-data-api-web-extract-db58f715
```

Example prompt: Can you extract the clean readable text from this article — https://techcrunch.com/2024/05/01/openai-raises-new-funding/ — and give me just the main content without all the ads and navigation?

## When to prefer this

Use this endpoint when you need the clean human-readable body text from a webpage and want a single pay-per-call API with no API key setup — paying $0.01 USDC per call via x402 on Base. Prefer over raw HTTP fetching when you need boilerplate-stripped, article-quality extraction without running your own parser.

## Known failure modes

- URL is unreachable or returns non-200 status — extraction fails or returns empty result
- URL points to a paywalled page — only partial or no content returned
- URL is a PDF or binary file — extraction may fail or return garbled content
- URL is a JavaScript-heavy SPA with no server-rendered content — extracted text may be empty
- Malformed or missing url query parameter — API returns error response
- Payment not settled via x402/USDC — 402 Payment Required response

## How this service works

Pay-per-call data utilities for AI agents (no API key, settle USDC on Base via x402). WEB: GET /audit?url= → structured site signals; GET /extract?url= → clean readable extraction. CRYPTO (multi-source, one call, cleaned & normalized): GET /snapshot?ids= → per-coin price+market+funding+sentiment merged from CoinGecko/Binance/F&G; GET /spread?symbol= → cross-venue best bid/ask & arb spread across Binance/Coinbase/Kraken/OKX; GET /funding → all perp funding rates, annualized APR, sorted extremes; GET /defi → DeFi macro (total TVL, top chains, stablecoin supply & 24h delta); GET /pulse → composite market-regime read (Fear&Greed + dominance + mcap delta + BTC funding → signal).

## Output

A JSON object containing the clean, readable extracted content of the target webpage — stripped of navigation, ads, and boilerplate HTML, leaving just the main body text and relevant structured signals.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "object",
   "properties": {
    "queryParams": {
     "type": "object",
     "properties": {
      "url": {
       "type": "string",
       "example": "https://article-to-extract.example"
      }
     }
    }
   }
  },
  "output": {
   "type": "object",
   "properties": {
    "result": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-data-api-web-extract-db58f715/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from 168.231.82.195.sslip.io](https://www.zero.xyz/host/168.231.82.195.sslip.io/llms.txt)