# ClawFetch URL Fetch

> ClawFetch URL Fetch is a paid API for AI agents from api.clawfetch.ai, paid per call via x402, $0.001/call, status healthy (last checked 2026-10-12, last successful call 2026-09-25).

Fetches any web page via a stealth HTTP client and returns clean, LLM-ready markdown with boilerplate, ads, and navigation stripped out.

## Facts

- Endpoint: POST https://api.clawfetch.ai/fetch?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: healthy
- Last checked: 2026-10-12
- Last successful call: 2026-09-25
- Success rate: 100% of calls made through Zero
- Activations on Zero: 3
- Tags: x402
- Canonical page: https://www.zero.xyz/c/clawfetch-url-fetch-0f01409f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wDdm880wrJG7x7uwmHifW

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 clawfetch-url-fetch-0f01409f -d '<json body>'
```

Example prompt: Fetch the content of https://techcrunch.com/2024/05/10/openai-funding-round/ and give me the clean article text as markdown, stripping out any ads and navigation.

## When to prefer this

Choose this endpoint when you need a fast, cheap single-page fetch of a publicly accessible URL and want clean markdown text back. It is the lowest-cost option ($0.001 per call) for static or server-rendered pages. Prefer the sibling headless browser endpoint when the target page requires JavaScript execution. Use this over general HTTP libraries when you want boilerplate stripping and bot-block avoidance built in.

## Known failure modes

- URL is unreachable or returns a non-200 status — error response with HTTP status code
- Target site employs advanced bot detection that the stealth client cannot bypass — may return empty or partial content
- Malformed or missing URL in request body — validation error
- Page content is behind a login wall — only publicly accessible content is returned
- JavaScript-heavy SPA with no static HTML — may return empty or minimal content (use headless browser endpoint instead)

## How this service works

Web scraping / URL fetch: retrieve any web page and return clean, LLM-ready markdown text. Strips boilerplate, ads, and navigation. Stealth HTTP client bypasses common bot blocks. Cheapest way to read a webpage.

## Output

Clean markdown text of the fetched web page with boilerplate, ads, and navigation removed, ready for ingestion by an LLM or further processing.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "URL to fetch"
  },
  "headers": {
   "type": "object"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "content": "<html>...</html>"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/clawfetch-url-fetch-0f01409f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.clawfetch.ai](https://www.zero.xyz/host/api.clawfetch.ai/llms.txt)