ContextQMD
Back to Eliza

Perplexity Plugin

packages/docs/plugin-registry/llm/perplexity.md

2.0.12.1 KB
Original Source
<Warning> This plugin is not yet available in the Eliza plugin registry. To use Perplexity models today, configure them through the [OpenRouter plugin](/plugin-registry/llm/openrouter) using the appropriate model ID. </Warning>

The Perplexity plugin connects Eliza agents to Perplexity's search-augmented language models. These models combine LLM reasoning with live web search, making them ideal for agents that need up-to-date information.

On-demand plugin. This plugin is resolved from the remote elizaOS plugin registry and auto-installs when its API key is detected. It is not included in Eliza's bundled plugins.json index.

Package: @elizaos/plugin-perplexity

Installation

bash
eliza plugins install @elizaos/plugin-perplexity

Auto-Enable

The plugin auto-enables when PERPLEXITY_API_KEY is present:

bash
export PERPLEXITY_API_KEY=pplx-...

Configuration

Environment VariableRequiredDescription
PERPLEXITY_API_KEYYesPerplexity API key from perplexity.ai

eliza.json Example

json
{
  "auth": {
    "profiles": {
      "default": {
        "provider": "perplexity",
        "model": "sonar-pro"
      }
    }
  }
}

Supported Models

ModelContextBest For
sonar-pro200kComplex research, multi-source synthesis
sonar128kGeneral-purpose search-augmented answers
sonar-reasoning-pro128kStep-by-step reasoning with citations
sonar-reasoning128kFast reasoning with web context

Features

  • Live web search integrated into every response
  • Citation-backed answers with source URLs
  • Streaming responses
  • Search-augmented generation (no separate RAG pipeline needed)
  • Ideal for research, fact-checking, and news-aware agents