# PennyRail Large Embedding Model

> PennyRail Large Embedding Model is a paid API for AI agents from pennyrail.vercel.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Generates large-scale vector embeddings for input data using a proven embedding model via PennyRail's pay-per-call settlement infrastructure

## Facts

- Endpoint: POST https://pennyrail.vercel.app/api/p/standard/ai.embed-large--proven-embed-large
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pennyrail-large-embedding-model-ec3932ae
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_bmqi28Ip1PxTHWpQamlOS

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-model-ec3932ae -d '<json body>'
```

Example prompt: Embed this product description using the large embedding model so I can store it in my vector database for semantic search: 'Ergonomic mesh office chair with lumbar support and adjustable armrests.'

## When to prefer this

Choose this endpoint when you need large-dimension, high-quality embeddings and are comfortable with per-call micropayment billing via x402/USDC. Prefer it over smaller embedding models when semantic fidelity and coverage matter more than latency or cost. It is well-suited for production RAG pipelines, semantic search indexing, and clustering tasks where embedding quality is critical.

## Known failure modes

- Missing required 'input' field returns a validation error
- Malformed input object may return a 400 or schema error
- Payment failure via x402 protocol results in 402 Payment Required before processing begins
- Oversized input exceeding model token limits may return an error or truncation
- Network timeout on the Vercel-hosted endpoint under high load

## How this service works

Machine-readable settlement service

## Output

Returns an object containing the embedding vector (a dense array of floating-point numbers) representing the semantic content of the input, produced by the proven-embed-large model. The response schema is open-ended and may include the vector array, model metadata, and token usage information.

## 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-model-ec3932ae/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)