# CortexCloud Embeddings

> CortexCloud Embeddings is a paid API for AI agents from api.cortexcloud.org, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Generates vector embeddings for a given text string using a specified embedding model, billed per call in USDC via x402.

## Facts

- Endpoint: GET https://api.cortexcloud.org/x402/v1/embeddings
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/cortexcloud-embeddings-5d77f2d9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_VacXpGON991ktK9UpCBeX

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 cortexcloud-embeddings-5d77f2d9
```

Example prompt: Can you embed this sentence using the gemini/text-embedding-004 model: 'The quick brown fox jumps over the lazy dog'?

## When to prefer this

Choose this endpoint when you need a pay-per-call embedding service with no API key management or subscription overhead, particularly in agent workflows that require dynamic, metered access. It is especially useful for AI agents operating autonomously with crypto wallets, needing OpenAI-compatible embedding outputs from multiple underlying providers (e.g. Gemini) without vendor lock-in.

## Known failure modes

- Missing or empty 'input' field returns a 400 validation error
- Invalid or unsupported model ID may return a 400 or 404 error
- Insufficient USDC balance or failed x402 payment results in a 402 Payment Required response
- Network timeout for large input texts
- Rate limiting if too many requests are sent in rapid succession

## How this service works

OpenAI-compatible AI and data API for agents. Pay per call in USDC on Base via x402 — no API keys, no subscriptions, no lock-in.

## Output

Returns a JSON object containing a 'data' array of embedding vectors (each an array of floats), the 'model' name used, and an 'object' field indicating the response type. The embedding array can be used directly for cosine similarity, nearest-neighbor search, or storage in a vector database.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string",
   "description": "Text to embed"
  },
  "model": {
   "type": "string",
   "description": "Embedding model id, e.g. gemini/text-embedding-004"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "format": "application/json",
 "example": {
  "id": "emb_abc",
  "data": [
   {
    "index": 0,
    "object": "embedding",
    "embedding": []
   }
  ],
  "usage": {
   "total_tokens": 0,
   "prompt_tokens": 0
  },
  "object": "list"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/cortexcloud-embeddings-5d77f2d9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.cortexcloud.org](https://www.zero.xyz/host/api.cortexcloud.org/llms.txt)