# OpenAI Embeddings via mm.family (x402)

> OpenAI Embeddings via mm.family (x402) is a paid API for AI agents from openai.mm.family, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-02).

Generates vector embeddings for text using OpenAI models (text-embedding-3-large, text-embedding-3-small, or text-embedding-ada-002), billed per call in USDC via x402 protocol

## Facts

- Endpoint: POST https://openai.mm.family/x402/v1/embeddings?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/openai-embeddings-via-mm-family-x402-f4bf639d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_m7e9FVUzydNrJ-zlPIu50

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 openai-embeddings-via-mm-family-x402-f4bf639d -d '<json body>'
```

Example prompt: Embed this text using text-embedding-3-large and return a float vector: 'The quick brown fox jumps over the lazy dog'

## When to prefer this

Choose this endpoint when you need OpenAI-quality text embeddings (especially text-embedding-3-large for highest accuracy) and want to pay per-call in USDC via the x402 micropayment protocol — ideal for AI agents operating autonomously without monthly subscription management. Prefer text-embedding-3-large for best semantic quality, text-embedding-3-small for cost efficiency, and text-embedding-ada-002 for compatibility with existing ada-002 indexes.

## Known failure modes

- Invalid model name returns 400 or model-not-found error
- Input text exceeds model token limit causing truncation or error
- Insufficient USDC balance causing x402 payment failure
- Malformed input (wrong type for 'input' field) causing schema validation error
- Unsupported encoding_format value causing 400 error
- Dimensions parameter out of range for chosen model causing error

## How this service works

OpenAI embeddings (text-embedding-3-large, text-embedding-3-small, text-embedding-ada-002), paid per call in USDC. OpenAI list $0.13 / $0.02 / $0.1 per 1M input tokens, plus $0.0005 (Base) or $0.0005 (Solana) per call; minimum $0.001 per call. Standard OpenAI body (model, input, dimensions, encoding_format). One endpoint per model: /x402/v1/models/<key>/embeddings. Rates: https://openai.mm.family/x402/pricing

## Output

Returns a JSON object containing a list of embedding objects, each with an index, object type, and a dense float vector (or base64-encoded equivalent). Also includes the model used and token usage statistics (prompt_tokens and total_tokens).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": [
    "string",
    "array"
   ]
  },
  "model": {
   "enum": [
    "text-embedding-3-large",
    "text-embedding-3-small",
    "text-embedding-ada-002"
   ],
   "type": "string"
  },
  "dimensions": {
   "type": "integer"
  },
  "encoding_format": {
   "enum": [
    "float",
    "base64"
   ],
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": [
   {
    "index": 0,
    "object": "embedding",
    "embedding": [
     0.01,
     -0.02
    ]
   }
  ],
  "model": "text-embedding-3-large",
  "usage": {
   "total_tokens": 1,
   "prompt_tokens": 1
  },
  "object": "list"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/openai-embeddings-via-mm-family-x402-f4bf639d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from openai.mm.family](https://www.zero.xyz/host/openai.mm.family/llms.txt)