# AgentBit Web Extract

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

Fetches any public URL and returns clean, structured content including title, meta description, main text, markdown, headings, outbound links, and page metadata with boilerplate removed.

## Facts

- Endpoint: POST https://agentbit.app/v1/web/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/agentbit-web-extract-88f58c29
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_AUQkjrLaipn091MG0xtjp

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 agentbit-web-extract-88f58c29 -d '<json body>'
```

Example prompt: Fetch the content of https://docs.example.com/getting-started and return the main text in markdown format, including all outbound links.

## When to prefer this

Choose this endpoint when you need to read and reason over the content of a specific public webpage — such as an article, documentation page, or product listing — and want clean, structured output (title, text, markdown, links) without writing custom scraping logic. It's especially useful for preprocessing web content before summarization, Q&A, or comparison tasks. Prefer it over a generic web search when you already have the URL and need the full page content rather than a snippet.

## Known failure modes

- URL is not publicly accessible or returns a 4xx/5xx HTTP error
- Paywalled or login-required content returns incomplete or no text
- JavaScript-heavy single-page apps may return empty content if render_fallback is false
- Malformed or non-HTTP URL input causes a validation error
- Very large pages may be truncated or time out
- Anti-scraping protections (Cloudflare, CAPTCHAs) may block extraction

## How this service works

Fetch any public URL and return clean, structured content: title, meta description, main text, markdown, headings, outbound links and page metadata. Removes scripts, navigation and boilerplate. Ideal for reading articles, docs and product pages before reasoning over them.

## Output

A structured JSON object containing the page title, meta description, clean main body text, markdown-formatted content, headings list, outbound links array, and additional page metadata — with scripts, navigation elements, and boilerplate stripped out.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string"
  },
  "include_links": {
   "type": "boolean"
  },
  "output_format": {
   "type": "string"
  },
  "render_fallback": {
   "type": "boolean"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com",
  "text": "Example Domain This domain is for use in illustrative examples in documents.",
  "links": [
   {
    "url": "https://www.iana.org/domains/example",
    "text": "More information..."
   }
  ],
  "title": "Example Domain",
  "headings": [
   {
    "text": "Example Domain",
    "level": 1
   }
  ],
  "markdown": "# Example Domain\n\nThis domain is for use in illustrative examples…",
  "metadata": {
   "viewport": "width=device-width, initial-scale=1"
  },
  "description": null
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentbit-web-extract-88f58c29/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentbit.app](https://www.zero.xyz/host/agentbit.app/llms.txt)