# PennyRail AI Small Text Embeddings

> PennyRail AI Small Text Embeddings is a paid API for AI agents from pennyrail.vercel.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Generates dense vector embeddings for text input using a small embedding model, accessible via pay-per-call settlement.

## Facts

- Endpoint: POST https://pennyrail.vercel.app/api/p/intel/ai.embed-small--text-embeddings
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pennyrail-ai-small-text-embeddings-c370e5bc
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_CCf6aleLtyJd30fheyI9p

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-small-text-embeddings-c370e5bc -d '<json body>'
```

Example prompt: Embed this text using the ai.embed-small model: 'Renewable energy adoption is accelerating globally due to falling solar panel costs.'

## When to prefer this

Choose this endpoint when you need cost-effective, low-latency text embeddings at $0.005 USDC per call and can tolerate a smaller model's representational capacity. Ideal for high-volume embedding pipelines (RAG, semantic search, clustering) where per-call cost matters and a 'small' model quality tier is sufficient. Prefer over larger embedding models when budget or throughput is the primary constraint.

## Known failure modes

- Missing or malformed 'input' object returns a 400 validation error
- Payment not fulfilled via x402 protocol results in a 402 Payment Required response
- Input text too long for the small model context window may cause truncation or error
- Upstream model unavailability on Vercel infrastructure causes 503 errors
- Empty input object may return a zero-vector or error depending on implementation

## How this service works

Machine-readable settlement service

## Output

Returns a JSON object containing the dense vector embedding (float array) representing the semantic content of the input text, generated by the small embedding model. The response schema is open-ended and may include the embedding array, model metadata, and token usage.

## 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-small-text-embeddings-c370e5bc/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)