# GEDX402 Vector Upsert

> GEDX402 Vector Upsert is a paid API for AI agents from search.gedx402.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Upserts raw embedding vectors into a namespaced vector index, paid per-call with USDC via x402 protocol, no API keys required.

## Facts

- Endpoint: GET https://search.gedx402.com/v1/vector/upsert
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-vector-upsert-84a3c386
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_DvHeD4mImY92-6ohos9h2

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-upsert-84a3c386
```

Example prompt: Store these two 768-dimension embeddings into my 'project-alpha' namespace: first vector with id 'doc-001' and values [0.12, 0.45, ...], second with id 'doc-002' and values [0.33, 0.77, ...], both with metadata {source: 'wiki'}.

## When to prefer this

Choose this endpoint when you need to store embedding vectors without managing API keys, want to pay per-call in USDC via x402 on Base, Polygon, Arbitrum, World, or Solana, and require namespace isolation per agent or project. Ideal for serverless RAG pipelines or agent memory systems built on Cloudflare Workers AI with 768-dim embeddings.

## Known failure modes

- Invalid vector dimensions (not 768 floats) — likely 422 or 400 error
- Namespace too short or too long (must be 2-64 chars) — validation error
- Missing required vector id or values fields — 400 bad request
- Payment not accepted or insufficient USDC balance — 402 payment required
- Vector array is empty — may return upserted: 0 or validation error

## How this service works

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

## Output

Returns a JSON object confirming how many vectors were upserted, e.g. {"upserted": 1}. No API key required; payment is handled automatically via x402 USDC on supported chains.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "vectors": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "id",
     "values"
    ],
    "properties": {
     "id": {
      "type": "string"
     },
     "values": {
      "type": "array",
      "items": {
       "type": "number"
      }
     },
     "metadata": {
      "type": "object"
     }
    }
   },
   "description": "Raw vectors for upsert (768 dims for default index)."
  },
  "namespace": {
   "type": "string",
   "description": "Agent collection id (2-64 chars). Isolates vectors per agent or project."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "upserted": 1
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-vector-upsert-84a3c386/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)