# Perplexity Embeddings via Locus x402

> Perplexity Embeddings via Locus x402 is a paid API for AI agents from perplexity.x402.paywithlocus.com, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-13).

Generates vector embeddings for text using Perplexity's pplx-embed models, paid per-call via x402 micropayments.

## Facts

- Endpoint: POST https://perplexity.x402.paywithlocus.com/perplexity/embed
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/perplexity-embeddings-via-locus-x402-e3a77b4f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_x9R5iSnji6B4IZhIYqvdp

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 perplexity-embeddings-via-locus-x402-e3a77b4f -d '<json body>'
```

Example prompt: Can you embed this text using the Perplexity pplx-embed-v1-4b model: 'The quick brown fox jumps over the lazy dog' — I need the vector representation for a semantic search index.

## When to prefer this

Choose this endpoint when you need pay-per-use text embeddings without a subscription commitment, especially in agentic workflows that require micropayment-native infrastructure. Prefer this over OpenAI or Cohere embedding APIs when you want x402-compatible billing or when you specifically want Perplexity's pplx-embed models for their semantic quality characteristics.

## Known failure modes

- Invalid model name returns an error — must be 'pplx-embed-v1-0.6b' or 'pplx-embed-v1-4b'
- Empty or missing input array causes a validation error
- Insufficient USDC balance or failed x402 payment results in request rejection
- Input text exceeding model token limits may be truncated or rejected
- Network timeout on large batches of strings

## How this service works

AI-powered search — Sonar chat with real-time web grounding, web search, and embeddings.

## Output

Returns a JSON object containing the embedding data (dense vector representations of the input text), a payment record showing 0.001 USDC settled, and a request ID with a status URL for tracking. The embedding vectors can be used directly in vector databases, similarity search, or downstream ML tasks.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "anyOf": [
    {
     "type": "string"
    },
    {
     "type": "array",
     "items": {
      "type": "string"
     }
    }
   ]
  },
  "model": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {},
  "payment": {
   "scheme": "exact",
   "settledUsdc": "0.001000",
   "authorizedMaxUsdc": "0.001000"
  },
  "request": {
   "id": "00000000-0000-4000-8000-000000000000",
   "statusUrl": "/requests/00000000-0000-4000-8000-000000000000"
  },
  "success": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/perplexity-embeddings-via-locus-x402-e3a77b4f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from perplexity.x402.paywithlocus.com](https://www.zero.xyz/host/perplexity.x402.paywithlocus.com/llms.txt)