# North Desk Web Search

> North Desk Web Search is a paid API for AI agents from annotated-pentium-lib-storm.trycloudflare.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Performs a web search query and returns results, charged at $0.01 USDC per call on Solana mainnet.

## Facts

- Endpoint: GET https://annotated-pentium-lib-storm.trycloudflare.com/v1/search
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/north-desk-web-search-cb4daa39
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_EpuHyn8rDwtiEYh8Rv11U

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 north-desk-web-search-cb4daa39
```

Example prompt: Search the web for the latest news on AI regulation in the EU and give me a summary of what you find.

## When to prefer this

Choose this endpoint when you need to retrieve current, live web information that is not available in a static knowledge base — especially for recent news, trending topics, real-time facts, or any information that may have changed after a model's training cutoff. At $0.01 per call it is cost-effective for moderate search volumes. Prefer the sibling URL-fetch endpoint if you already have a specific URL and need full content rather than a search result list.

## Known failure modes

- Empty or missing query parameter returns an error
- Network timeout if downstream search provider is slow
- Payment failure if USDC balance on Solana is insufficient
- Rate limiting if too many requests are made in quick succession
- Query too long or contains unsupported characters

## How this service works

Web search. $0.01 USDC on Solana mainnet.

## Output

Returns web search results for the given query, typically including relevant page titles, URLs, and text snippets drawn from across the web.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "query": {
   "type": "string",
   "description": "Search query"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/north-desk-web-search-cb4daa39/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from annotated-pentium-lib-storm.trycloudflare.com](https://www.zero.xyz/host/annotated-pentium-lib-storm.trycloudflare.com/llms.txt)