# CortexCloud Batch Embeddings API

> CortexCloud Batch Embeddings API is a paid API for AI agents from api.cortexcloud.org, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Generates vector embeddings for a batch of up to 100 text strings in a single call, returning dense float arrays compatible with OpenAI embedding format

## Facts

- Endpoint: GET https://api.cortexcloud.org/x402/v1/embeddings/batch
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/cortexcloud-batch-embeddings-api-063c10ad
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_EyYxvcIlMJGBAmKKRdiN2

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-batch-embeddings-api-063c10ad
```

Example prompt: Embed these 50 product descriptions into vectors using the text-embedding-3-small model so I can load them into my vector database for semantic search.

## When to prefer this

Choose this endpoint when you need to vectorize multiple texts in a single round-trip, saving latency and cost compared to calling a single-embedding endpoint repeatedly. It is ideal for RAG ingestion pipelines, semantic search index building, or clustering tasks where you have 2–100 texts ready to embed at once. The OpenAI-compatible response format means it slots directly into existing tooling. The pay-per-call USDC model on Base is preferable when you want no subscription overhead and programmatic micropayment billing for agents.

## Known failure modes

- Input array exceeds 100 items — batch must be split into smaller chunks
- Invalid or unsupported model ID — returns error indicating unknown model
- Payment failure via x402 — call rejected if USDC payment on Base is not completed
- Empty input array — may return empty data array or validation error
- Texts too long for the model's context window — individual items may be truncated or rejected

## 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 with a data array where each item contains an index, object type ('embedding'), and the embedding float array for the corresponding input text. Also includes a usage object with total_tokens and prompt_tokens counts for the batch.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "List of texts (max 100) to embed"
  },
  "model": {
   "type": "string",
   "description": "Embedding model id"
  }
 }
}
```

## Response schema (JSON Schema)

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

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/cortexcloud-batch-embeddings-api-063c10ad/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)