Connect to Google's Gemini models through the Generative AI API.
Configuration
| Field | Required | Example |
|---|
| Application Name | Yes | my-gemini-app |
| Model Name | Yes | gemini-2.0-flash, gemini-2.5-pro |
| API Key | Yes | AIza... |
Getting Your API Key
- Go to Google AI Studio
- Click Get API Key
- Create a new API key or use an existing one
- Copy and securely store your key
Popular Models
| Model | Description |
|---|
gemini-3.0-pro | Most powerful model for multimodal understanding and agentic tasks |
gemini-2.5-pro | Adaptive thinking, leads WebDev Arena and LMArena |
gemini-2.5-flash | Best for large-scale processing, agentic use cases (54% SWE-bench) |
gemini-2.5-flash-lite | Lowest latency and cost, optimized for throughput |
gemini-2.5-flash-image | State-of-the-art for targeted image transformation |
For the complete list of available models, visit the Gemini API Models Documentation.
Advanced Parameters
| Parameter | Type | Description |
|---|
max_output_tokens | integer | Maximum tokens in response |
temperature | float | Randomness (0.0-2.0) |
top_p | float | Nucleus sampling |
top_k | integer | Top-k sampling |
Setup Steps
- Navigate to AI Applications → New Application
- Select Model Providers tab
- Click Google
- Enter your Application Name and API Key
- Select your desired Model Name
- Configure Advanced Settings (optional)
- Click Test Response to verify (optional)
- Review and submit