# GPUOps AI Inference Proxy - Embeddings

> GPUOps AI Inference Proxy - Embeddings is a paid API for AI agents from ai.gpuops.io, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-14).

Generates vector embeddings for input text using a selected model via an OpenAI-compatible API, with pay-per-call USDC billing on Base.

## Facts

- Endpoint: POST https://ai.gpuops.io/v1/embeddings
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gpuops-ai-inference-proxy-embeddings-af6010ae
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_zUqQ6PvDKIEjeBNzg9i7I

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 gpuops-ai-inference-proxy-embeddings-af6010ae -d '<json body>'
```

Example prompt: Turn this product description into a text embedding using the text-embedding-3-small model: 'Handcrafted leather wallet with RFID blocking, 6 card slots, and a slim profile.'

## When to prefer this

Choose this endpoint when you need pay-per-call embedding generation without a monthly subscription, want OpenAI API compatibility so you can drop it into existing RAG or semantic search pipelines, need access to a wide variety of embedding models (63 available), and prefer on-chain USDC micropayments on Base for transparent, programmatic billing.

## Known failure modes

- Invalid or unsupported model name returns an error — must be one of the 63 supported models
- Empty or missing input text field causes a validation error
- Insufficient USDC balance or failed x402 payment results in a 402 Payment Required response
- Oversized input exceeding the model's context window returns a token limit error
- Network timeouts for very large inputs or under high server load

## How this service works

OpenAI-compatible AI inference API with 63 models. x402 pay-per-call with USDC on Base.

## Output

Returns an OpenAI-compatible response object containing a list of embedding vectors (arrays of floating-point numbers), the model used, and token usage statistics. The embedding vector can be stored in a vector database or used directly for similarity computations.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string"
  },
  "model": {
   "type": "string"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gpuops-ai-inference-proxy-embeddings-af6010ae/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from ai.gpuops.io](https://www.zero.xyz/host/ai.gpuops.io/llms.txt)