Skip to main content

Google Gemini

Use Google’s Gemini models with Agentium through the unified ModelProvider interface. Gemini offers strong multi-modal capabilities—vision, audio, and native file handling.

Setup

Install the Google GenAI SDK (required by Agentium for Gemini support):

Factory

string
required
The Gemini model identifier.
object
Optional configuration. See Config below.

Supported Models


Config

string
Google API key. If omitted, uses GOOGLE_API_KEY environment variable.

Example


Multi-Modal Support

Gemini supports vision, audio, and file content. Pass multi-modal content via ContentPart[] in messages:

Files & Documents

Gemini handles files natively — including PDF, CSV, XLSX, and more. It’s the only provider that supports XLSX directly:

Supported File Types

Gemini processes file content natively via inlineData, making it the most versatile provider for document analysis tasks.

Realtime / Voice (Gemini Live)

For real-time voice agents, use googleLive() to create a Google Gemini Live provider:
googleLive() is a shorthand for new GoogleLiveProvider(). It accepts the same config:
Requires: npm install @google/genai See the Voice Agents docs for full details.

Full Example