Google Gemini LLM | LiveKit Documentation

Create a new agent in your browser using this model

Overview

Google Gemini models are available in LiveKit Agents through LiveKit Inference and the Gemini plugin. Pricing for LiveKit Inference is available on the pricing page.

Model name	Model ID	Providers
Gemini 3 Pro	google/gemini-3-pro	google
Gemini 3 Flash	google/gemini-3-flash	google
Gemini 2.5 Pro	google/gemini-2.5-pro	google
Gemini 2.5 Flash	google/gemini-2.5-flash	google
Gemini 2.5 Flash Lite	google/gemini-2.5-flash-lite	google

LiveKit Inference

Use LiveKit Inference to access Gemini models without a separate Google API key.

Usage

To use Gemini, use the LLM class from the inference module:

from livekit.agents import AgentSession, inference

session = AgentSession(
    llm=inference.LLM(
        model="google/gemini-2.5-flash-lite",
        extra_kwargs={
            "max_completion_tokens": 1000
        }
    ),
    # ... tts, stt, vad, turn_detection, etc.
)

import { AgentSession, inference } from '@livekit/agents';

session = new AgentSession({
    llm: new inference.LLM({ 
        model: "google/gemini-2.5-flash-lite", 
        modelOptions: { 
            max_completion_tokens: 1000 
        }
    }),
    // ... tts, stt, vad, turn_detection, etc.
});

Parameters

modelstringRequired

The model ID from the models list.

providerstringOptional

Set a specific provider to use for the LLM. Refer to the models list for available providers. If not set, LiveKit Inference uses the best available provider, and bills accordingly.

extra_kwargsdictOptional

Additional parameters to pass to the Gemini Chat Completions API, such as max_completion_tokens.

In Node.js this parameter is called modelOptions.

String descriptors

As a shortcut, you can also pass a model descriptor string directly to the llm argument in your AgentSession:

from livekit.agents import AgentSession

session = AgentSession(
    llm="google/gemini-2.5-flash-lite",
    # ... tts, stt, vad, turn_detection, etc.
)

import { AgentSession } from '@livekit/agents';

session = new AgentSession({
    llm: "google/gemini-2.5-flash-lite",
    // ... tts, stt, vad, turn_detection, etc.
});

Plugin

Use the Google plugin to connect directly to Google's Gemini API with your own API key.

Available in

Python

Node.js

Installation

Install the plugin from PyPI:

uv add "livekit-agents[google]~=1.4"

pnpm add @livekit/agents-plugin-google@1.x

Authentication

The Google plugin requires authentication based on your chosen service:

For Vertex AI, you must set the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path of the service account key file. For more information about mounting files as secrets when deploying to LiveKit Cloud, see File-mounted secrets .
For Google Gemini API, set the GOOGLE_API_KEY environment variable.

Usage

Use Gemini within an AgentSession or as a standalone LLM service. For example, you can use this LLM in the Voice AI quickstart.

from livekit.plugins import google

session = AgentSession(
    llm=google.LLM(
        model="gemini-3-flash-preview",
    ),
    # ... tts, stt, vad, turn_detection, etc.
)

import * as google from '@livekit/agents-plugin-google';

const session = new voice.AgentSession({
    llm: google.LLM(
        model: "gemini-3-flash-preview",
    ),
    // ... tts, stt, vad, turn_detection, etc.
});

Parameters

This section describes some of the available parameters. For a complete reference of all available parameters, see the plugin reference.

modelChatModels | strOptionalDefault: gemini-3-flash-preview

ID of the model to use. For a full list, see Gemini models.

api_keystrOptionalEnv: GOOGLE_API_KEY

API key for Google Gemini API.

vertexaiboolOptionalDefault: false

True to use Vertex AI; false to use Google AI.

projectstrOptionalEnv: GOOGLE_CLOUD_PROJECT

Google Cloud project to use (only if using Vertex AI). Required if using Vertex AI and the environment variable isn't set.

locationstrOptionalEnv: GOOGLE_CLOUD_LOCATION

Google Cloud location to use (only if using Vertex AI). Required if using Vertex AI and the environment variable isn't set.

Provider tools

Google Gemini supports provider tools that enable the model to use built-in capabilities executed on the model server. These tools can be used alongside function tools defined in your agent's codebase.

Available tools include:

GoogleSearch: Perform keyword search, semantic search, user search, and thread fetch on Google
GoogleMaps: Perform search for places and businesses using Google Maps
URLContext: Provide context for URLs
ToolCodeExecution: Execute code snippets

Current limitations

Currently only the Gemini Live API supports using provider tools along with function tools.

When using text models, only provider tools or function tools can be used. See issue #53 for more details.

from livekit.plugins import google
from google.genai import types

agent = MyAgent(
    llm=google.LLM(
        model="gemini-2.5-flash",
    ),
    tools=[google.tools.GoogleSearch()],
)

import * as google from '@livekit/agents-plugin-google';

// currently, Agents JS supports provider tools via `geminiTools` parameter.

const agent = new MyAgent({
    llm: google.LLM(
        model: "gemini-2.5-flash",
        geminiTools: [new google.types.GoogleSearch()],
    ),
    // ... tts, stt, vad, turn_detection, etc.
});

Additional resources

The following resources provide more information about using Google Gemini with LiveKit Agents.

Python plugin

Reference GitHub PyPI

Node.js plugin

Reference GitHub NPM

Gemini docs

Google Gemini documentation.

Voice AI quickstart

Get started with LiveKit Agents and Google Gemini.

Google AI ecosystem guide

Overview of the entire Google AI and LiveKit Agents integration.