# x402.shizu.me OpenAI-Compatible Embeddings

> x402.shizu.me OpenAI-Compatible Embeddings is a paid API for AI agents from x402.shizu.me, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-20).

Generates text embeddings via a drop-in OpenAI-compatible endpoint, paid per call in USDC with no account or API key required.

## Facts

- Endpoint: POST https://x402.shizu.me/v1/embeddings?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/x402-shizu-me-openai-compatible-embeddings-dc42d689
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FOTndLYpIR_5Ep7gjOCrl

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 x402-shizu-me-openai-compatible-embeddings-dc42d689 -d '<json body>'
```

Example prompt: Embed these 5 product descriptions into vectors so I can load them into my vector database for semantic search — use the text-embedding-3-small model with 1536 dimensions.

## When to prefer this

Choose this endpoint when you need OpenAI-compatible embeddings without wanting to manage API keys or accounts — ideal for agent pipelines that want pay-per-call USDC billing, or when you want to drop in a compatible embeddings endpoint alongside the same provider's chat completions. Best for batches up to 16 items; for larger bulk jobs, loop calls here rather than using a managed embedding service.

## Known failure modes

- Input exceeds 16 items or 8KB total — request rejected with an error
- Payment fails or USDC balance insufficient — call returns payment error
- Unsupported model name passed — returns model-not-found error
- Malformed input (non-string, null) — returns validation error
- Network timeout if input is near the size limit and processing is slow

## How this service works

Drop-in OpenAI embeddings endpoint — same base_url as /v1/chat/completions, pay per call in USDC, no account or key. POST {input: string|array (max 16 items, 8KB total), model?, dimensions?}. Returns the standard {data:[{embedding:[...]}], usage} shape. Flat price per call. The bulk-loop primitive for RAG ingestion, semantic search, dedup, clustering — point your OpenAI SDK here and embed.

## Output

Returns a standard OpenAI-shaped JSON response with a `data` array of embedding objects (each containing an `embedding` float array and an `index`), plus a `usage` object with token counts. The response is structurally identical to OpenAI's /v1/embeddings output, making it a drop-in replacement.

## Request schema (JSON Schema)

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

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x402-shizu-me-openai-compatible-embeddings-dc42d689/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.shizu.me](https://www.zero.xyz/host/x402.shizu.me/llms.txt)