# Perplexity Embed

> Perplexity Embed is a paid API for AI agents from Perplexity at perplexity.mpp.paywithlocus.com, paid per call via MPP, ~$0.001 (dynamic), status unknown (last checked 2026-10-09).

Converts text into dense vector embeddings using Perplexity's pplx-embed-v1 models (0.6B or 4B parameter variants)

## Facts

- Endpoint: POST https://perplexity.mpp.paywithlocus.com/perplexity/embed?utm_source=zero.xyz
- Price: ~$0.001 (dynamic)
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-09
- Activations on Zero: 0
- Provider: Perplexity
- Docs: https://docs.perplexity.ai
- Website: https://perplexity.ai
- Tags: search, ai-search, web-grounding, sonar, ai
- Canonical page: https://www.zero.xyz/c/perplexity-embed-1ac0164d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_CbYngl-mryZRXV2tc3x9_

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-embed-1ac0164d -d '<json body>'
```

Example prompt: Use Perplexity's pplx-embed-v1-4b model to embed this text so I can store it in my vector database: 'Quantum computing leverages superposition and entanglement to perform calculations exponentially faster than classical computers.'

## When to prefer this

Choose this endpoint when you need fast, high-quality text embeddings from Perplexity's purpose-built embed models (pplx-embed-v1). Prefer the 4B variant for higher fidelity semantic representations and the 0.6B variant for speed-sensitive or cost-sensitive workloads. Well-suited for building RAG pipelines alongside Perplexity's Sonar chat and search endpoints.

## Known failure modes

- Invalid model name — must be 'pplx-embed-v1-0.6b' or 'pplx-embed-v1-4b'
- Missing required 'input' field returns validation error
- Input text exceeds model context window
- Authentication or payment failure returns 401/402
- Empty string input may return error or zero vector

## How this service works

Generate vector embeddings for semantic search, clustering, and RAG. Supports MRL (Matryoshka) dimensionality reduction and INT8/BINARY quantization.

## Output

A dense floating-point embedding vector representing the semantic content of the input text, produced by the specified pplx-embed-v1 model (0.6B or 4B). The vector can be used for downstream tasks like similarity search, clustering, or retrieval.

## Example request

```json
{
 "input": "The quick brown fox jumps over the lazy dog.",
 "model": "pplx-embed-v1-4b"
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "model",
  "input"
 ],
 "properties": {
  "input": {
   "anyOf": [
    {
     "type": "string"
    },
    {
     "type": "array",
     "items": {
      "type": "string"
     }
    }
   ],
   "description": "Text to embed. Single string or array of strings."
  },
  "model": {
   "type": "string",
   "description": "Embedding model: 'pplx-embed-v1-0.6b' or 'pplx-embed-v1-4b'"
  }
 },
 "additionalProperties": true
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/perplexity-embed-1ac0164d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from perplexity.mpp.paywithlocus.com](https://www.zero.xyz/host/perplexity.mpp.paywithlocus.com/llms.txt)