Google Gemini Configuration

Configure a Google Gemini API key for use with RoostGPT.

Step 1: Generate an API Key

1. Go to Google AI Studio
2. Sign in with your Google account
3. Click "Create API key"
4. Select an existing Google Cloud project or create a new one
5. Click "Create API key in existing project"
6. Copy the key immediately — store it securely

Step 2: Add to RoostGPT

Web UI (Connector)

1. Click Connectors in the top navigation bar → AI Model
2. Select Google Gemini
3. Enter your API key
4. Select your default model

CLI (.env file)

AI_TYPE=gemini
GEMINI_API_KEY=your-api-key
GEMINI_MODEL=gemini-2.5-pro

Supported Models

Model	Context Window	Best For	Key Features
Gemini 2.5 Pro	1024K in / 64K out	Complex API testing, large codebases	Deep Think mode, long context
Gemini 2.5 Flash	1024K in / 64K out	Fast, cost-effective	Best price-performance, agentic use
Gemini 2.5 Flash-Lite	1024K in / 64K out	High-volume, low-latency	Most cost-effective
Gemini 2.0 Flash	1024K in / 8K out	Modern app testing	Native tool use, improved speed
Gemini 2.0 Flash-Lite	1024K in / 8K out	Budget projects	Cost-efficient, low latency

Recommended: gemini-2.5-pro for accuracy, gemini-2.5-flash for cost-performance balance.

Notes

• The 1M context window on Gemini 2.5 models makes them ideal for large codebases or extensive requirement documents.
• Gemini models support vision capabilities natively, making them suitable for UI test generation.
• API keys are free to create; usage is billed through your Google Cloud project.