# Tollkit Web Search API (Google Results)

> Tollkit Web Search API (Google Results) is a paid API for AI agents from web.tollkit.dev, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-13).

Searches the web via Google and returns ranked results (title, URL, snippet, date) plus answer boxes as clean JSON, powered by Serper

## Facts

- Endpoint: POST https://web.tollkit.dev/search?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tollkit-web-search-api-google-results-09bdfbdb
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_BBPvVA8H_ICA6MXvxn-io

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 tollkit-web-search-api-google-results-09bdfbdb -d '<json body>'
```

Example prompt: Search the web for 'best open-source LLM models 2025' and give me the top 5 results with titles, URLs, and snippets — US results please.

## When to prefer this

Choose this endpoint when you need fast, current, Google-ranked web search results in clean JSON without setting up API keys or accounts — payment is handled inline via x402/USDC. Prefer it over custom scrapers or static knowledge when freshness matters (news, recent events, current prices). Ideal for AI agents that need sourced, ranked results rather than a single extracted page. Use alongside Tollkit Extract if you want to follow up by scraping a specific result page.

## Known failure modes

- Query string exceeds 400 characters — request rejected
- num parameter outside 1–10 range — validation error
- Invalid country code format (not 2 letters) — rejected
- Serper upstream outage — 5xx error propagated
- Payment failure via x402 — 402 response, no search executed
- Empty or ambiguous query may return low-quality or irrelevant results

## How this service works

Web search for AI agents: search the web for any query and get ranked Google results (title, URL, snippet, date) as clean JSON, plus the answer box when there is one. Fast, current results for research, fact checks and finding sources. Results via Serper.

## Output

A JSON array of ranked web results, each containing title, URL, snippet text, and publication date. If Google returns an answer box for the query, that is included as a separate top-level field. Number of results is controlled by the caller (1–10).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "num": {
   "type": "integer",
   "default": 5,
   "maximum": 10,
   "minimum": 1
  },
  "query": {
   "type": "string",
   "maxLength": 400,
   "description": "What to search for."
  },
  "country": {
   "type": "string",
   "pattern": "^[a-zA-Z]{2}$",
   "description": "Two-letter country code for localised results, e.g. \"us\"."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tollkit-web-search-api-google-results-09bdfbdb/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from web.tollkit.dev](https://www.zero.xyz/host/web.tollkit.dev/llms.txt)