# PennyRail AI Embed Small – Embedding Vector

> PennyRail AI Embed Small – Embedding Vector 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 a small embedding vector representation for a given input object, accessible via a pay-per-call settlement API

## Facts

- Endpoint: POST https://pennyrail.vercel.app/api/p/intel/ai.embed-small--embedding-vector
- 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-ai-embed-small-embedding-vector-1ababfb8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_7lRZxafnX8-6zP0nYtYfy

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-embed-small-embedding-vector-1ababfb8 -d '<json body>'
```

Example prompt: Can you generate a small embedding vector for this text: 'The quick brown fox jumps over the lazy dog'? I need the vector to power a semantic search index.

## When to prefer this

Prefer this endpoint when you need a lightweight, pay-per-call embedding generation with no subscription commitment and x402-compatible micropayment settlement. It is ideal for agents that need to embed individual text chunks on-demand without managing API keys or monthly quotas. The 'small' model variant is best when speed and cost-efficiency are prioritised over maximum embedding dimensionality.

## Known failure modes

- Missing required 'input' field returns a validation error
- Malformed input object may return a 400 bad request
- Payment not settled or insufficient USDC balance may result in a 402 Payment Required response
- Model overload or cold-start latency on Vercel serverless may cause timeouts
- Overly large input objects may exceed size limits and return an error

## How this service works

Machine-readable settlement service

## Output

Returns a JSON object containing the embedding vector (a dense array of floating-point numbers) representing the input. The vector can be used for downstream tasks such as semantic search, clustering, classification, or retrieval-augmented generation.

## 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-embed-small-embedding-vector-1ababfb8/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)