Google GenAI Plugin

Use Google AI (Gemini) and Vertex AI models with Genkit

Google GenAI Plugin

The @genkit-ai/google-genai plugin provides a unified interface to connect with Google’s generative AI models, offering access through both the Gemini Developer API and Vertex AI. It replaces the previous googleAI and vertexAI plugins.

Installation

npm install @genkit-ai/google-genai

Configuration

This unified plugin exports two main initializers:

• googleAI: Access models via the Gemini Developer API using API key authentication
• vertexAI: Access models via Google Cloud Vertex AI

Using Gemini Developer API (googleAI)

Ideal for quick prototyping and access to models available in Google AI Studio.

Authentication: Requires a Google AI API Key from Google AI Studio. Provide the key via GEMINI_API_KEY or GOOGLE_API_KEY environment variables, or pass it in the plugin configuration.

import { genkit } from 'genkit';
import { googleAI } from '@genkit-ai/google-genai';

const ai = genkit({
  plugins: [
    googleAI(),
    // Or with an explicit API key:
    // googleAI({ apiKey: 'your-api-key' }),
  ],
});

Using Vertex AI (vertexAI)

Suitable for applications leveraging Google Cloud’s AI infrastructure.

Authentication Methods:

• Application Default Credentials (ADC): Standard method for production. Uses credentials from the environment (service account on GCP, user credentials from gcloud auth application-default login locally). Requires a Google Cloud Project with billing and Vertex AI API enabled.

• Vertex AI Express Mode: Streamlined way to try Vertex AI features using just an API key, without billing setup. Ideal for quick experimentation with generous free tier quotas. Learn more about Express Mode.

import { genkit } from 'genkit';
import { vertexAI } from '@genkit-ai/google-genai';

const ai = genkit({
  plugins: [
    // Using Application Default Credentials (Recommended for full features)
    vertexAI({ location: 'us-central1' }), // Regional endpoint
    // vertexAI({ location: 'global' }),      // Global endpoint

    // OR

    // Using Vertex AI Express Mode (Easy to start, some limitations)
    // vertexAI({ apiKey: process.env.VERTEX_EXPRESS_API_KEY }),
  ],
});

Note: When using Express Mode, don’t provide projectId and location in the plugin config.

Using Both Google AI and Vertex AI

You can configure both plugins to access models or features from both services:

import { genkit } from 'genkit';
import { googleAI, vertexAI } from '@genkit-ai/google-genai';

const ai = genkit({
  plugins: [
    googleAI(),
    vertexAI(),
  ],
});

Available Models

Gemini Models

• gemini-2.5-flash - Fast, efficient model for most tasks
• gemini-2.5-pro - Advanced reasoning and complex tasks
• gemini-1.5-flash - Previous generation fast model
• gemini-1.5-pro - Previous generation advanced model

Image Generation

• imagen-3.0-generate-002 - High-quality image generation

Embeddings

• gemini-embedding-001 - Text embeddings (Google AI)
• text-embedding-005 - Text embeddings (Vertex AI)

Music Generation (Vertex AI Only)

• lyria-002 - AI music generation

Usage Examples

Text Generation with Google AI

import { genkit } from 'genkit';
import { googleAI } from '@genkit-ai/google-genai';

const ai = genkit({
  plugins: [googleAI()],
});

const response = await ai.generate({
  model: googleAI.model('gemini-2.5-flash'),
  prompt: 'Tell me something interesting about Google AI.',
});

console.log(response.text());

Text Generation with Vertex AI

import { genkit } from 'genkit';
import { vertexAI } from '@genkit-ai/google-genai';

const ai = genkit({
  plugins: [vertexAI()],
});

const response = await ai.generate({
  model: vertexAI.model('gemini-2.5-pro'),
  prompt: 'Explain Vertex AI in simple terms.',
});

console.log(response.text());

Text Embedding

With Google AI:

import { genkit } from 'genkit';
import { googleAI } from '@genkit-ai/google-genai';

const ai = genkit({
  plugins: [googleAI()],
});

const embeddings = await ai.embed({
  embedder: googleAI.embedder('gemini-embedding-001'),
  content: 'Embed this text.',
});

With Vertex AI:

import { genkit } from 'genkit';
import { vertexAI } from '@genkit-ai/google-genai';

const ai = genkit({
  plugins: [vertexAI()],
});

const embeddings = await ai.embed({
  embedder: vertexAI.embedder('text-embedding-005'),
  content: 'Embed this text.',
});

Image Generation (Imagen)

With Google AI:

import { genkit } from 'genkit';
import { googleAI } from '@genkit-ai/google-genai';

const ai = genkit({
  plugins: [googleAI()],
});

const response = await ai.generate({
  model: googleAI.model('imagen-3.0-generate-002'),
  prompt: 'A beautiful watercolor painting of a castle in the mountains.',
});

const generatedImage = response.media();

With Vertex AI:

import { genkit } from 'genkit';
import { vertexAI } from '@genkit-ai/google-genai';

const ai = genkit({
  plugins: [vertexAI()],
});

const response = await ai.generate({
  model: vertexAI.model('imagen-3.0-generate-002'),
  prompt: 'A beautiful watercolor painting of a castle in the mountains.',
});

const generatedImage = response.media();

Music Generation (Lyria - Vertex AI Only)

import { genkit } from 'genkit';
import { vertexAI } from '@genkit-ai/google-genai';

const ai = genkit({
  plugins: [vertexAI()],
});

const response = await ai.generate({
  model: vertexAI.model('lyria-002'),
  prompt: 'A relaxing, instrumental piano track.',
});

const generatedAudio = response.media();

Key Differences

Google AI (googleAI)

• Easier setup for smaller projects
• Great for prototyping with Google AI Studio
• Uses API keys for authentication
• Access to Gemini and Imagen models

Vertex AI (vertexAI)

• Enterprise-ready with Google Cloud IAM
• Integrates with other Vertex AI services
• Broader range of models and features
• Supports Lyria music generation
• Fine-tuning capabilities
• Robust governance and compliance
• Express Mode for easy experimentation

Links

• Google AI Studio
• Vertex AI
• Vertex AI Express Mode
• Source Code