# Agent Internet Runtime - Web Content Extraction

> Agent Internet Runtime - Web Content Extraction is a paid API for AI agents from api.agentinternetruntime.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Extracts structured content, metadata, links, and description from any web URL for AI agent consumption

## Facts

- Endpoint: POST https://api.agentinternetruntime.com/v1/extract
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-internet-runtime-web-content-extraction-8982f05b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_yHqFyaoCm7AIpzrXkPrzq

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-internet-runtime-web-content-extraction-8982f05b -d '<json body>'
```

Example prompt: Can you pull the full content, title, metadata, and any links from https://example.com/article so I can analyze what's on that page?

## When to prefer this

Choose this endpoint when an AI agent needs to read, parse, and extract structured content from a live web URL — especially when you need both the human-readable content AND machine-readable metadata and discovered links in one call. Prefer this over generic HTTP fetches when you need AIR's collective intelligence layer for trust and structured output, or when building agents that need to browse and reason about web pages programmatically.

## Known failure modes

- URL is unreachable or returns non-200 HTTP status — success: false with no data
- Malformed or invalid URL input — request rejected with error
- Page requires JavaScript rendering not supported by extractor — incomplete content returned
- Payment of $0.01 USDC not fulfilled via x402 — 402 Payment Required response
- Rate limiting or server-side blocking of crawler — success: false or timeout
- Private/authenticated pages return empty or partial content

## How this service works

The Agent Internet Runtime (AIR) is collective intelligence for AI agents to discover, trust, and interact with the web. Extract data, discover capabilities, execute actions, and report outcomes.

## Output

Returns a JSON object with success boolean and a data object containing: the page URL, title, full text content, structured metadata, a description, and an array of discovered links found on the page.

## Example request

```json
{
 "url": "https://example.com",
 "options": {
  "cache": "bypass",
  "timeout": 5000
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "http",
 "schema": {
  "type": "object",
  "properties": {
   "data": {
    "type": "object",
    "properties": {
     "url": {
      "type": "string"
     },
     "title": {
      "type": "string"
     },
     "content": {
      "type": "string"
     },
     "metadata": {
      "type": "object"
     },
     "description": {
      "type": "string"
     },
     "discoveredLinks": {
      "type": "array",
      "items": {
       "type": "string"
      }
     }
    }
   },
   "success": {
    "type": "boolean"
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-internet-runtime-web-content-extraction-8982f05b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agentinternetruntime.com](https://www.zero.xyz/host/api.agentinternetruntime.com/llms.txt)