Gemini CLI

This tutorial shows you how to integrate the Gemini CLI with haimaker Proxy, allowing you to route requests through haimaker's unified interface.

info

This integration is supported from haimaker v1.73.3-nightly and above.

Benefits of using gemini-cli with haimaker

When you use gemini-cli with haimaker you get the following benefits:

Developer Benefits:

• Universal Model Access: Use any haimaker supported model (Anthropic, OpenAI, Vertex AI, Bedrock, etc.) through the gemini-cli interface.
• Higher Rate Limits & Reliability: Load balance across multiple models and providers to avoid hitting individual provider limits, with fallbacks to ensure you get responses even if one provider fails.

Proxy Admin Benefits:

• Centralized Management: Control access to all models through a single haimaker proxy instance without giving your developers API Keys to each provider.
• Budget Controls: Set spending limits and track costs across all gemini-cli usage.

Prerequisites

Before you begin, ensure you have:

• Node.js and npm installed on your system
• A running haimaker Proxy instance
• A valid haimaker Proxy API key
• Git installed for cloning the repository

Quick Start Guide

Step 1: Install Gemini CLI

Clone the Gemini CLI repository and navigate to the project directory:

npm install -g @google/gemini-cli

Step 2: Configure Gemini CLI for haimaker Proxy

Configure the Gemini CLI to point to your haimaker Proxy instance by setting the required environment variables:

export GOOGLE_GEMINI_BASE_URL="http://localhost:4000"
export GEMINI_API_KEY=sk-1234567890

Note: Replace the values with your actual haimaker Proxy configuration:

• BASE_URL: The URL where your haimaker Proxy is running
• GEMINI_API_KEY: Your haimaker Proxy API key

Step 3: Build and Start Gemini CLI

Build the project and start the CLI:

gemini

Step 4: Test the Integration

Once the CLI is running, you can send test requests. These requests will be automatically routed through haimaker Proxy to the configured Gemini model.

The CLI will now use haimaker Proxy as the backend, giving you access to haimaker's features like:

• Request/response logging
• Rate limiting
• Cost tracking
• Model routing and fallbacks

Advanced

Use Anthropic, OpenAI, Bedrock, etc. models on gemini-cli

In order to use non-gemini models on gemini-cli, you need to set a model_group_alias in the haimaker Proxy config. This tells haimaker that requests with model = gemini-2.5-pro should be routed to your desired model from any provider.

Anthropic

Route gemini-2.5-pro requests to Claude Sonnet:

proxy_config.yaml

model_list:
  - model_name: claude-sonnet-4-20250514
    litellm_params:
      model: anthropic/claude-3-5-sonnet-20241022
      api_key: os.environ/ANTHROPIC_API_KEY

router_settings:
  model_group_alias: {"gemini-2.5-pro": "claude-sonnet-4-20250514"}

OpenAI

Route gemini-2.5-pro requests to GPT-4o:

proxy_config.yaml

model_list:
  - model_name: gpt-4o-model
    litellm_params:
      model: gpt-4o
      api_key: os.environ/OPENAI_API_KEY

router_settings:
  model_group_alias: {"gemini-2.5-pro": "gpt-4o-model"}

Bedrock

Route gemini-2.5-pro requests to Claude on Bedrock:

proxy_config.yaml

model_list:
  - model_name: bedrock-claude
    litellm_params:
      model: bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0
      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
      aws_region_name: us-east-1

router_settings:
  model_group_alias: {"gemini-2.5-pro": "bedrock-claude"}

Multi-Provider Load Balancing

All deployments with model_name=anthropic-claude will be load balanced. In this example we load balance between Anthropic and Bedrock.

proxy_config.yaml

model_list:
  - model_name: anthropic-claude
    litellm_params:
      model: anthropic/claude-3-5-sonnet-20241022
      api_key: os.environ/ANTHROPIC_API_KEY  
  - model_name: anthropic-claude
    litellm_params:
      model: bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0
      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
      aws_region_name: us-east-1

router_settings:
  model_group_alias: {"gemini-2.5-pro": "anthropic-claude"}

With this configuration, when you use gemini-2.5-pro in the CLI, haimaker will automatically route your requests to the configured provider(s) with load balancing and fallbacks.

Troubleshooting

If you encounter issues:

1. Connection errors: Verify that your haimaker Proxy is running and accessible at the configured GOOGLE_GEMINI_BASE_URL
2. Authentication errors: Ensure your GEMINI_API_KEY is valid and has the necessary permissions
3. Build failures: Make sure all dependencies are installed with npm install