# GEDX402 Vector Search Query

> GEDX402 Vector Search Query is a paid API for AI agents from search.gedx402.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-13).

Performs semantic vector search over a named namespace, returning ranked document matches with optional metadata, paid per-query via USDC on multiple chains

## Facts

- Endpoint: GET https://search.gedx402.com/v1/search/query
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-vector-search-query-64dc738b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9w3YVJ0cCnLSOrD3jYihH

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 gedx402-vector-search-query-64dc738b
```

Example prompt: Search my 'customer-support' namespace for the top 5 documents most relevant to 'how do I reset my password', and include their stored metadata in the results.

## When to prefer this

Choose this endpoint when you need pay-per-query semantic vector search without provisioning API keys or managing embedding infrastructure — especially in agentic workflows that already handle USDC micropayments on Base, Polygon, Arbitrum, World, or Solana. Ideal for agents needing to query isolated per-project or per-agent document namespaces at low cost ($0.02/call).

## Known failure modes

- Payment not received or insufficient USDC — HTTP 402 returned before query executes
- Namespace not found or empty — returns count 0 with empty matches array
- top_k out of range (must be 1-50) — validation error or clamped result
- Query string missing or empty — 400 bad request
- Chain/network payment failure causing transaction timeout
- Namespace string too short (<2) or too long (>64 chars) — validation error

## How this service works

x402 workers ai. pay with usdc on base, polygon, arbitrum, world, or solana. no api keys.

## Output

A JSON object with a count field and a matches array; each match includes a document ID, a floating-point similarity score (e.g. 0.91), and optionally a metadata object containing the original text and any stored fields.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "query": {
   "type": "string",
   "description": "Natural-language search query."
  },
  "top_k": {
   "type": "integer",
   "description": "Max results (1-50)."
  },
  "namespace": {
   "type": "string",
   "description": "Agent collection id (2-64 chars). Isolates vectors per agent or project."
  },
  "return_metadata": {
   "type": "boolean",
   "description": "Include stored metadata in matches."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "count": 1,
  "matches": [
   {
    "id": "doc-1",
    "score": 0.91,
    "metadata": {
     "text": "..."
    }
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-vector-search-query-64dc738b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from search.gedx402.com](https://www.zero.xyz/host/search.gedx402.com/llms.txt)