# PennyRail AI Embeddings v1

> PennyRail AI Embeddings v1 is a paid API for AI agents from pennyrail.vercel.app, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-15).

Generates vector embeddings for input data via a pay-per-call settlement endpoint using the x402 micropayment protocol

## Facts

- Endpoint: POST https://pennyrail.vercel.app/api/p/mini/ai.v1-embeddings--v1-embeddings
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pennyrail-ai-embeddings-v1-31c54e78
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_66r3nUNtY0Jbm91N7AsPC

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 pennyrail-ai-embeddings-v1-31c54e78 -d '<json body>'
```

Example prompt: Generate a vector embedding for this text: 'The quick brown fox jumps over the lazy dog' — I need it for a semantic similarity search pipeline.

## When to prefer this

Choose this endpoint when you need on-demand, pay-per-call text embeddings without a subscription or API key commitment, especially in agentic workflows where micropayments via x402 are already supported. Ideal for low-volume or variable-load embedding needs billed per request in USDC.

## Known failure modes

- Missing or malformed 'input' field returns a validation error
- Payment not settled via x402 protocol returns HTTP 402 Payment Required
- Oversized input exceeding token limits may return a 400 or truncation error
- Network or provider backend failures return 5xx errors
- Invalid content type or malformed JSON body returns 400

## How this service works

Machine-readable settlement service

## Output

Returns a JSON object containing the vector embedding (numerical array) representing the semantic content of the input, suitable for downstream tasks like similarity search, clustering, or storage in a vector database.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "additionalProperties": true
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pennyrail-ai-embeddings-v1-31c54e78/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from pennyrail.vercel.app](https://www.zero.xyz/host/pennyrail.vercel.app/llms.txt)