# Venice Web Search

> Venice Web Search is a paid API for AI agents from api.venice.ai, paid per call via x402, $10/call, status unknown (last checked 2026-10-11).

Searches the web using Brave or Google and returns structured results with titles, URLs, content snippets, and dates — with privacy-preserving query handling.

## Facts

- Endpoint: POST https://api.venice.ai/api/v1/augment/search?utm_source=zero.xyz
- Price: $10/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402, ai_ml
- Canonical page: https://www.zero.xyz/c/venice-web-search-2c091886
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_oDtgQ6Syp16mqhJrT0Y2U

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 venice-web-search-2c091886 -d '<json body>'
```

Example prompt: Search the web for the latest developments in quantum computing and give me the top 5 results — use Brave Search for privacy.

## When to prefer this

Use this endpoint when you need live, current web search results with privacy guarantees — especially when using Brave's Zero Data Retention mode where queries are never logged. Prefer over generic scraping when you want structured multi-result data (title, URL, snippet, date) without handling raw HTML. Choose Brave for maximum privacy; choose Google when broader index coverage is needed with anonymized proxying.

## Known failure modes

- 402 Payment Required — insufficient x402 wallet balance, response includes top-up instructions
- 400 Bad Request — missing required 'query' field or query exceeds 400 characters
- 400 Bad Request — limit out of range (must be 1–20)
- 401 Unauthorized — missing or invalid Bearer API key or X-Sign-In-With-X header
- 500 Internal Server Error — upstream search provider unavailable
- Empty results array — query returned no matches from the chosen provider

## How this service works

Search the web and return results directly. Returns structured search results including titles, URLs, content snippets, and dates.

**Search providers:**
- `brave` (default) — Brave Search with Zero Data Retention (ZDR). Search queries are never stored or logged by the search provider.
- `google` — Google Search with anonymized queries. Searches are proxied through Venice's infrastructure so that your identity is not associated with the search request sent to Google. Venice does not store or log search queries.

**Authentication:** This endpoint accepts either a Bearer API key or an `X-Sign-In-With-X` header for x402 wallet-based authentication. When using x402, a `402 Payment Required` response indicates insufficient balance and includes top-up instructions.

## Output

Returns a JSON object with the echoed query and an array of up to 20 results, each containing a title, URL, content snippet, and publication date (when available).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "query"
 ],
 "properties": {
  "limit": {
   "type": "integer",
   "default": 10,
   "example": 10,
   "maximum": 20,
   "minimum": 1,
   "description": "Maximum number of results to return (default: 10, max: 20)"
  },
  "query": {
   "type": "string",
   "example": "latest news about AI",
   "maxLength": 400,
   "minLength": 1,
   "description": "The search query"
  },
  "search_provider": {
   "enum": [
    "google",
    "brave"
   ],
   "type": "string",
   "example": "brave",
   "description": "Search provider to use. \"brave\" uses Brave Search with Zero Data Retention (ZDR) for maximum privacy — search queries are never stored or logged. \"google\" uses Google Search with anonymized queries — searches are proxied through Venice's infrastructure so that your identity is not associated with the search request sent to Google. Venice does not store or log search queries. Defaults to \"brave\"."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "query",
  "results"
 ],
 "properties": {
  "query": {
   "type": "string",
   "description": "The search query that was executed"
  },
  "results": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "title",
     "url",
     "content",
     "date"
    ],
    "properties": {
     "url": {
      "type": "string",
      "description": "The URL of the search result"
     },
     "date": {
      "type": "string",
      "description": "The date of the search result, if available"
     },
     "title": {
      "type": "string",
      "description": "The title of the search result"
     },
     "content": {
      "type": "string",
      "description": "A snippet or description of the search result"
     }
    }
   },
   "description": "The search results"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/venice-web-search-2c091886/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.venice.ai](https://www.zero.xyz/host/api.venice.ai/llms.txt)