Gemini CLI Integration

Configure Gemini CLI to use Adaptive’s intelligent routing infrastructure that automatically selects the optimal Google Gemini model for each task.

Intelligent Gemini model selection with automatic routing. Works as a drop-in replacement for Gemini CLI’s API backend, selecting between Gemini 2.5 Pro, Flash, and Flash Lite based on task complexity with cost optimization built-in.

Benefits of Using Gemini CLI with Adaptive

When you integrate Gemini CLI with Adaptive, you unlock powerful capabilities:

Intelligent Model Selection: Adaptive automatically selects the optimal Gemini model (2.5 Pro, 2.5 Flash, or 2.5 Flash Lite) based on your task complexity
Cost Optimization: Automatically routes simple tasks to Flash Lite, moderate tasks to Flash, and complex tasks to Pro, optimizing costs without sacrificing quality
Higher Reliability: Automatic fallbacks and retry logic ensure consistent responses
Usage Analytics: Monitor model usage, costs, and performance in real-time
Simplified Configuration: Single API key for all Gemini model variants

Get Your Adaptive API Key

Quick Setup

Run Automated Installer

curl -fsSL https://raw.githubusercontent.com/Egham-7/adaptive/main/scripts/installers/gemini-cli.sh | bash

The installer will automatically:

Install Gemini CLI if not present (via npm)
Configure environment variables for Adaptive routing
Add configuration to your shell profile (~/.bashrc, ~/.zshrc, etc.)
Verify the installation

Verify Configuration

gemini --version
echo $GEMINI_API_KEY
echo $GOOGLE_GEMINI_BASE_URL

Start Using

gemini "explain quantum computing"

Adaptive will automatically route your request to the optimal Gemini model.

Manual Installation

If you prefer to set up Gemini CLI manually or need more control over the installation process:

Step 1: Install Gemini CLI

npm install -g @google/gemini-cli

Step 2: Configure Environment Variables

# Gemini CLI with Adaptive LLM API Configuration
export GEMINI_API_KEY="your-adaptive-api-key-here"
export GOOGLE_GEMINI_BASE_URL="https://api.llmadaptive.uk/v1beta"

Step 3: Apply Configuration

# For Bash/Zsh
source ~/.bashrc  # or ~/.zshrc

# For Fish
source ~/.config/fish/config.fish

# Or restart your terminal

Step 4: Verify Installation

gemini --version
gemini "test connection"

Alternative Setup Methods

export ADAPTIVE_API_KEY='your-api-key-here'
curl -fsSL https://raw.githubusercontent.com/Egham-7/adaptive/main/scripts/installers/gemini-cli.sh | bash
# The installer will automatically configure your shell

Advanced Configuration

Specifying Gemini Models

Configure which Gemini model to use by default:

# Use Gemini 2.5 Pro for complex tasks
export GEMINI_MODEL='gemini:gemini-2.5-flash-lite'
gemini "write a complex algorithm"

Model Selection

When GEMINI_MODEL is not set or empty, Adaptive intelligently selects the best Gemini model for each task based on:

Task complexity: Analyzes prompt complexity to select the optimal model
Performance requirements: Matches model capabilities to task needs
Cost optimization: Balances performance and cost automatically
Availability: Automatic fallback if a model is unavailable

Available Gemini Models

Model	Best For	Speed	Cost
`gemini-2.5-flash-lite`	Complex reasoning, deep analysis	Slower	Higher
`gemini-2.5-flash`	Moderate tasks, balanced performance	Fast	Medium
`gemini-2.5-flash-lite`	Simple tasks, quick responses	Fastest	Lowest

Usage Examples

# Start interactive chat session
gemini

# Or with a specific prompt
gemini "help me debug this code"

Troubleshooting

Installation Issues

Problem: Gemini CLI installation failsSolutions:

Ensure Node.js 18+ is installed: node --version

Install Node.js if needed:

# Using nvm (recommended)
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash
nvm install 22

Check npm permissions: npm config get prefix
Try with sudo (not recommended): sudo npm install -g @google/gemini-cli

Authentication Errors

Problem: “Unauthorized” or “Invalid API key” errorsSolutions:

Verify your API key at llmadaptive.uk/dashboard

Check environment variables are set:

echo $GEMINI_API_KEY
echo $GOOGLE_GEMINI_BASE_URL

Ensure variables are exported in your shell config:

# Bash/Zsh
source ~/.bashrc  # or ~/.zshrc

# Fish
source ~/.config/fish/config.fish

Restart your terminal if changes were made to shell config
Verify the base URL is correct: https://api.llmadaptive.uk/v1

Connection Errors

Problem: Cannot connect to Adaptive APISolutions:

Check internet connectivity
Verify base URL is correct: echo $GOOGLE_GEMINI_BASE_URL

Test API directly:

curl -X POST https://api.llmadaptive.uk/v1/chat/completions \
  -H "Authorization: Bearer $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash-lite",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Check if your network/firewall blocks the API endpoint

Model Routing Issues

Problem: Requests not routing to expected modelsSolutions:

Check if model alias is configured (if using advanced routing)
Verify your Adaptive proxy configuration
Review model names in your requests
Check Adaptive dashboard for routing logs
Clear the ADAPTIVE_MODEL environment variable for intelligent routing:
```
unset ADAPTIVE_MODEL
```

Performance Issues

Problem: Slow response times or timeoutsSolutions:

Check Adaptive dashboard for provider status
Verify rate limits aren’t exceeded
Consider using load balancing across multiple providers
Check your internet connection speed
Review model selection—some models are faster than others

Uninstallation

If you need to remove Gemini CLI or revert to Google’s API:

Remove Gemini CLI

npm uninstall -g @google/gemini-cli

Remove Environment Variables

Edit your shell config file and remove these lines:

# Gemini CLI with Adaptive LLM API Configuration
export GEMINI_API_KEY="..."
export GOOGLE_GEMINI_BASE_URL="..."

Reload Shell Configuration

source ~/.bashrc  # or ~/.zshrc or ~/.config/fish/config.fish

Next Steps

Monitor Usage & Savings

Track your cost savings and usage analytics in real-time

API Documentation

Learn about Adaptive’s API capabilities and advanced features

More CLI Tools

Explore other CLI tools with Adaptive integration

Advanced Routing

Learn about intelligent model routing and load balancing

Was this page helpful? Contact us at info@llmadaptive.uk for feedback or assistance with your Gemini CLI integration.

Getting Started

Key Features

Framework Integrations

Developer Tools

Examples

API Reference

Support

Gemini CLI Integration

Benefits of Using Gemini CLI with Adaptive

Get Your Adaptive API Key

Quick Setup

Manual Installation

Step 1: Install Gemini CLI

Step 2: Configure Environment Variables

Step 3: Apply Configuration

Step 4: Verify Installation

Alternative Setup Methods

Advanced Configuration

Specifying Gemini Models

Model Selection

Available Gemini Models

Usage Examples

Troubleshooting

Uninstallation

Next Steps

Monitor Usage & Savings

API Documentation

More CLI Tools

Advanced Routing

Getting Started

Key Features

Framework Integrations

Developer Tools

Examples

API Reference

Support

​Benefits of Using Gemini CLI with Adaptive

​Get Your Adaptive API Key

​Quick Setup

​Manual Installation

​Step 1: Install Gemini CLI

​Step 2: Configure Environment Variables

​Step 3: Apply Configuration

​Step 4: Verify Installation

​Alternative Setup Methods

​Advanced Configuration

​Specifying Gemini Models

​Model Selection

​Available Gemini Models

​Usage Examples

​Troubleshooting

​Uninstallation

​Next Steps

Monitor Usage & Savings

API Documentation

More CLI Tools

Advanced Routing

Benefits of Using Gemini CLI with Adaptive

Get Your Adaptive API Key

Quick Setup

Manual Installation

Step 1: Install Gemini CLI

Step 2: Configure Environment Variables

Step 3: Apply Configuration

Step 4: Verify Installation

Alternative Setup Methods

Advanced Configuration

Specifying Gemini Models

Model Selection

Available Gemini Models

Usage Examples

Troubleshooting

Uninstallation

Next Steps