# PennyRail Large Embedding Generation

> PennyRail Large Embedding Generation is a paid API for AI agents from pennyrail.vercel.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Generates large-scale vector embeddings from input data via a paid per-call API using x402 micropayment settlement

## Facts

- Endpoint: POST https://pennyrail.vercel.app/api/p/standard/ai.embed-large--large-embeddings
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pennyrail-large-embedding-generation-83327b96
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hQnDY5pqZlGkZt-vKaH98

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-large-embedding-generation-83327b96 -d '<json body>'
```

Example prompt: Generate a large embedding vector for this text so I can use it for semantic similarity search: 'The quick brown fox jumps over the lazy dog' — use the large embedding model.

## When to prefer this

Choose this endpoint when you need large, high-dimensional embeddings (as opposed to small or compressed variants) and are operating in an x402 micropayment-enabled environment where per-call billing at $0.01 USDC is acceptable. Well-suited for agentic pipelines that require pay-per-use embedding without API key management overhead.

## Known failure modes

- Payment not included or insufficient — x402 payment required at $0.01 USDC per call
- Missing required 'input' field in request body — returns validation error
- Malformed input object — unprocessable entity error
- Service unavailable on Vercel deployment — 5xx error
- Input too large for the embedding model — may return size limit error

## How this service works

Machine-readable settlement service

## Output

Returns an object containing the large embedding vector representation of the input, suitable for downstream tasks such as semantic search, clustering, similarity matching, or feeding into ML models. The response schema is open-ended and may include the vector array and associated metadata.

## 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-large-embedding-generation-83327b96/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)