Google Gemini

Google Gemini is Google's family of multimodal AI models, offering some of the largest context windows available and strong performance across coding, reasoning, and document analysis tasks.

Website: https://ai.google.dev/

Getting an API Key

1. Sign Up/Sign In: Go to Google AI Studio. Sign in with your Google account.
2. Get API Key: Navigate to aistudio.google.com/apikey.
3. Create a Key: Click "Create API Key" and select or create a Google Cloud project.
4. Copy the Key: Copy the API key immediately and store it securely.

Supported Models

Cline supports the following Google Gemini models:

Gemini 3 Series (Latest)

• gemini-3.1-pro-preview (Default) - Latest pro model with 1M context, thinking support, and tiered pricing ($2.00-$4.00/M input)
• gemini-3-flash-preview - Fast model with 1M context and thinking level support ($0.30-$0.50/M input)

Gemini 2.5 Series

• gemini-2.5-pro - High-performance model with 1M context and thinking budget ($1.25-$2.50/M input)
• gemini-2.5-flash - Fast and affordable with 1M context and thinking support ($0.30/M input)
• gemini-2.5-flash-lite-preview-06-17 - Ultra-affordable lite variant ($0.10/M input)

Gemini 2.0 Series

• gemini-2.0-flash-001 - Fast model with 1M context and prompt caching ($0.10/M input)
• gemini-2.0-flash-lite-preview-02-05 - Lite variant (free during preview)
• gemini-2.0-pro-exp-02-05 - Pro experimental with 2M context (free during preview)
• gemini-2.0-flash-thinking-exp-01-21 - Thinking experimental with 1M context (free)
• gemini-2.0-flash-thinking-exp-1219 - Earlier thinking experimental (free)
• gemini-2.0-flash-exp - Flash experimental with 1M context (free)

Gemini 1.5 Series (Legacy)

• gemini-1.5-flash-002 - Fast model with tiered pricing and prompt caching
• gemini-1.5-flash-exp-0827 - Flash experimental (free)
• gemini-1.5-flash-8b-exp-0827 - Compact 8B flash (free)
• gemini-1.5-pro-002 - Pro model with 2M context
• gemini-1.5-pro-exp-0827 - Pro experimental (free)
• gemini-exp-1206 - Experimental with 2M context (free)

Configuration in Cline

1. Open Cline Settings: Click the settings icon (⚙️) in the Cline panel.
2. Select Provider: Choose "Google Gemini" from the "API Provider" dropdown.
3. Enter API Key: Paste your Google AI API key into the "Gemini API Key" field.
4. Select Model: Choose your desired model from the "Model" dropdown.

Thinking / Reasoning Support

Gemini 3 and 2.5 models support thinking/reasoning capabilities:

• Gemini 3 Pro/Flash: Support thinking levels (low, high) that control reasoning depth
• Gemini 2.5 Pro/Flash: Support thinking budgets that cap the number of thinking tokens

Enable extended thinking in Cline settings to leverage these capabilities for complex coding and reasoning tasks.

Tips and Notes

• Large Context Windows: Gemini models offer up to 2M token context windows, making them excellent for large codebases and document analysis.
• Prompt Caching: Gemini 2.5+ and select 2.0 models support prompt caching for reduced costs on repeated queries.
• Image Support: All Gemini models support image inputs for multimodal tasks.
• Tiered Pricing: Some models have tiered pricing based on context usage (e.g., lower prices under 200K tokens).
• Free Experimental Models: Many experimental models are available at no cost during their preview period.
• Pricing: Refer to the Google AI pricing page for the latest information.