Perplexity with LiveKit Agents

Use Perplexity’s Agent API as the LLM brain of a LiveKit voice agent.

Overview

Perplexity’s Agent API is compatible with the OpenAI Responses API, so it works as a drop-in LLM for LiveKit Agents through livekit-plugins-openai’s openai.responses.LLM class, pointed at Perplexity’s base URL.

LiveKit Agents is an open-source framework for building realtime voice and multimodal AI agents. For new integrations, use the Perplexity Agent API via openai.responses.LLM — not the livekit-plugins-perplexity plugin or openai.LLM.with_perplexity(), which both call the legacy Chat Completions endpoint. Learn more at livekit.io.

Installation

pip install "livekit-agents" "livekit-plugins-openai"

API Key Setup

Set your Perplexity API key as an environment variable and pass it to the constructor:

export PERPLEXITY_API_KEY="your_api_key_here"

Get API Key

Generate your API key from the Perplexity dashboard.

Quick Start

Use openai.responses.LLM anywhere a LiveKit AgentSession expects an LLM:

import os

from livekit.agents import Agent, AgentSession
from livekit.plugins import openai, silero

session = AgentSession(
    llm=openai.responses.LLM(
        model="openai/gpt-5.6-sol",
        base_url="https://api.perplexity.ai/v1",   # SDK appends /responses -> POST /v1/responses
        api_key=os.environ["PERPLEXITY_API_KEY"],  # required: constructor does not read PERPLEXITY_API_KEY
    ),
    stt=openai.STT(),
    tts=openai.TTS(),
    vad=silero.VAD.load(),
)

agent = Agent(
    instructions="You are a helpful voice assistant. Use web search to answer with up-to-date information.",
    tools=[openai.tools.WebSearch()],  # Perplexity's built-in web_search tool
)

# Run the session inside your LiveKit room entrypoint

Because the Agent API is OpenAI-Responses-compatible, the OpenAI plugin talks to https://api.perplexity.ai/v1 with no other changes.

Configuration

openai.responses.LLM needs two settings to target Perplexity - base_url and an explicit api_key (the constructor does not read PERPLEXITY_API_KEY on its own):

import os

from livekit.plugins import openai

llm = openai.responses.LLM(
    model="openai/gpt-5.6-sol",
    base_url="https://api.perplexity.ai/v1",
    api_key=os.environ["PERPLEXITY_API_KEY"],
)

Perplexity’s built-in tools (like web_search, shown in the Quick Start) attach to the Agent, not to the LLM.

Available Models

The integration works with any model exposed through the Perplexity Agent API, addressed as provider/model (for example openai/gpt-5.6-sol). See the full list on our models page.

Links & Resources

LiveKit Agents Docs

Build realtime voice and multimodal agents with LiveKit.

OpenAI Plugin Source

The livekit-plugins-openai source, including the Responses LLM.

Agent API Quickstart

Request, response, and tool contract used above.

Agent API Models

Available models and pricing.

Support

Need help with the integration?

• Browse the LiveKit Agents documentation
• Review our FAQ