# Agent Wonderland Web Search

> Agent Wonderland Web Search is a paid API for AI agents from api.agentwonderland.com, paid per call via x402, $0.1/call, status unknown (last checked 2026-10-12).

Searches the web (or news/images) and returns full page content as markdown in a single API call, powered by Firecrawl, with per-request USDC payment via x402.

## Facts

- Endpoint: POST https://api.agentwonderland.com/x402/endpoints/web-search?utm_source=zero.xyz
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-wonderland-web-search-06ac1042
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_2404HQP4iCBfJ9MJEl5Qn

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-wonderland-web-search-06ac1042 -d '<json body>'
```

Example prompt: Search the web for the top 5 results about 'best AI agent frameworks in 2026' from the past month and give me the full page content for each result.

## When to prefer this

Choose this endpoint when you need both web search results AND the full content of matching pages in a single call, rather than making separate search and scrape requests. Ideal for agents that need real-time, up-to-date information with full article or page text — especially useful for news monitoring, research, and content extraction tasks. Prefer this over raw search APIs when markdown-formatted full page content is required downstream.

## Known failure modes

- Query returns no results for very niche or obscure topics
- Scraping fails for paywalled or bot-protected pages, returning partial content
- Time filter may return zero results if the topic has no recent coverage
- Exceeding the limit of 10 results per call
- Payment failure via x402 if USDC balance is insufficient
- Slow or unavailable pages may timeout during content scraping

## How this service works

Agent Wonderland is a marketplace and payment layer for agent-ready APIs. This endpoint runs Web Search: Search the web and get full page content in one call. Powered by Firecrawl. Use x402 to pay per request with USDC; Agent Wonderland handles execution, receipts, refunds, and builder payouts.

## Output

Returns a list of search result objects, each containing the page URL, title, snippet, and (when scrape_content is true) the full page content rendered as markdown. Results are filtered by source type (web, news, or images) and optional time range.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "limit": {
   "type": "integer",
   "title": "Limit",
   "default": 5,
   "maximum": 10,
   "minimum": 1,
   "description": "Number of results (max 10)"
  },
  "query": {
   "type": "string",
   "title": "Query",
   "description": "Search query",
   "json_schema_extra": {
    "example": "best AI agent frameworks 2026"
   }
  },
  "source": {
   "type": "string",
   "title": "Source",
   "default": "web",
   "description": "Source type: web, news, or images"
  },
  "time_filter": {
   "type": "string",
   "title": "Time Filter",
   "default": "",
   "description": "Time filter: qdr:d (24h), qdr:w (week), qdr:m (month)"
  },
  "scrape_content": {
   "type": "boolean",
   "title": "Scrape Content",
   "default": true,
   "description": "Also fetch full page content as markdown"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-wonderland-web-search-06ac1042/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agentwonderland.com](https://www.zero.xyz/host/api.agentwonderland.com/llms.txt)