# CheapestInference Embeddings API

> CheapestInference Embeddings API is a paid API for AI agents from api.cheapestinference.com, paid per call via x402, $20/call, status unknown (last checked 2026-09-15).

Generates vector embeddings for text input using 200+ open-source AI models via an OpenAI-compatible API with flat-rate pricing

## Facts

- Endpoint: POST https://api.cheapestinference.com/v1/embeddings
- Price: $20/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/cheapestinference-embeddings-api-ffb33b1b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_fvfE7shXwHUAfvsiziFMR

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 cheapestinference-embeddings-api-ffb33b1b -d '<json body>'
```

Example prompt: Convert these product descriptions into vector embeddings using a good open-source embedding model — I want to use them for semantic search in my product catalog.

## When to prefer this

Choose this endpoint when you need OpenAI-compatible text embeddings from open-source models at a predictable flat rate, especially when per-token costs are prohibitive for large batches, or when you want to pay with USDC on Base. Prefer over OpenAI embeddings when cost predictability or crypto payment is required.

## Known failure modes

- Invalid or unsupported model identifier returns an error
- Input text too long for the selected model's context window
- Payment of $20 USDC not fulfilled, causing 402 Payment Required
- Malformed request body returns 400 Bad Request
- Rate limiting or quota exceeded returns 429 Too Many Requests

## How this service works

Access 200+ open-source AI models through a single OpenAI-compatible API. Flat-rate pricing with no per-token charges. Pay with card or USDC on Base.

## Output

Returns a JSON object with a 'data' array containing embedding vectors for each input text, in OpenAI-compatible format, ready for use in semantic search, RAG pipelines, or similarity computations.

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "array"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/cheapestinference-embeddings-api-ffb33b1b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.cheapestinference.com](https://www.zero.xyz/host/api.cheapestinference.com/llms.txt)