# GEDX402 Vector Search

> GEDX402 Vector Search is a paid API for AI agents from search.gedx402.com, paid per call via x402, $0.015/call, status unknown (last checked 2026-09-14).

Performs semantic vector similarity search against a named namespace, returning the top-K nearest neighbors to a 768-dimensional query vector

## Facts

- Endpoint: GET https://search.gedx402.com/v1/vector/query
- Price: $0.015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-vector-search-17d81c09
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_teluyVZAzQ0Va4Qnoa99L

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-17d81c09
```

Example prompt: Search my 'support-docs' namespace for the 10 closest matches to this 768-dimensional embedding vector, and include the stored metadata in the results.

## When to prefer this

Choose this endpoint when you need keyless, pay-per-query vector similarity search with no API key registration, especially in agentic workflows that manage crypto payments via x402 on Base, Polygon, Arbitrum, World, or Solana. Ideal for agents that need to isolate vector collections per project using namespaces and want to pay $0.015 USDC per call on-chain rather than managing subscription credentials.

## Known failure modes

- Vector dimension mismatch — query vector must be exactly 768 dimensions
- Namespace not found or empty — returns count:0 and empty matches array
- top_k out of range — must be between 1 and 50
- Payment failure — USDC payment on specified chain not confirmed, request rejected with 402
- Malformed vector array — non-numeric values or wrong shape cause validation error
- Namespace string too short or too long — must be 2–64 characters

## 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' integer and a 'matches' array, each match containing the vector ID, similarity score, and optionally the raw vector values and stored metadata fields depending on the return_values and return_metadata flags.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "top_k": {
   "type": "integer",
   "description": "Max results (1-50)."
  },
  "vector": {
   "type": "array",
   "items": {
    "type": "number"
   },
   "description": "768-dim query vector."
  },
  "namespace": {
   "type": "string",
   "description": "Agent collection id (2-64 chars). Isolates vectors per agent or project."
  },
  "return_values": {
   "type": "boolean",
   "description": "Include raw vector values in matches."
  },
  "return_metadata": {
   "type": "boolean",
   "description": "Include stored metadata in matches."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "count": 0,
  "matches": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-vector-search-17d81c09/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)