# PennyRail Semantic Embedding (ai.embed-small)

> PennyRail Semantic Embedding (ai.embed-small) is a paid API for AI agents from pennyrail.vercel.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Generates small semantic embedding vectors from input data for use in similarity search, clustering, and retrieval-augmented generation pipelines.

## Facts

- Endpoint: POST https://pennyrail.vercel.app/api/p/intel/ai.embed-small--semantic-embedding
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pennyrail-semantic-embedding-ai-embed-small-d123b00c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_S494UgBy2OqE3N3TZd8eW

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-semantic-embedding-ai-embed-small-d123b00c -d '<json body>'
```

Example prompt: Generate a semantic embedding vector for the text 'climate change mitigation strategies in developing economies' so I can compare it against my document index for similarity search.

## When to prefer this

Choose this endpoint when you need a lightweight, pay-per-use semantic embedding via x402 micropayment with no API key setup, especially in agent workflows where you want cost-controlled, on-demand vectorization without a subscription to OpenAI Embeddings or Cohere.

## Known failure modes

- Missing or malformed 'input' field returns a 400-level error
- Payment not included or insufficient USDC balance triggers 402 Payment Required
- Oversized input exceeding model token limits may cause truncation or rejection
- Network timeouts on Vercel cold starts may produce 503 responses
- Ambiguous or empty input object may return zero-vector or error

## How this service works

Machine-readable settlement service

## Output

Returns an object containing the semantic embedding vector (array of floats) representing the input in a high-dimensional semantic space, suitable for cosine similarity comparisons, nearest-neighbor search, or downstream ML tasks.

## 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-semantic-embedding-ai-embed-small-d123b00c/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)