Skip to main content
Gemini CLI is Google’s official command-line AI tool, allowing you to interact with Gemini models directly from your terminal. By configuring the OpenAI-compatible mode, you can easily connect it to ePhone AI.

​
Installation

Make sure you have Python 3.9+ installed: 
pip install gemini-cli

​
Configuration & Launch

Gemini CLI can be configured via environment variables. 
echo 'export OPENAI_API_KEY="sk-your-api-key"' >> ~/.zshrc
echo 'export OPENAI_API_BASE="https://api.ephone.ai/v1"' >> ~/.zshrc
source ~/.zshrc

[Environment]::SetEnvironmentVariable("OPENAI_API_KEY", "sk-your-api-key", "User")
[Environment]::SetEnvironmentVariable("OPENAI_API_BASE", "https://api.ephone.ai/v1", "User")

​
Start Interactive Mode

gemini --model gpt-4o

​
Key Features

FeatureDescription
Interactive ChatEnter questions directly in the terminal, and Gemini CLI will return real-time answers
Pipeline InputSupports piping code or logs to Gemini CLI for analysis
File ReadingCan read local file contents as context

​
Usage Examples

​
Analyze a Code File

cat main.py | gemini "Analyze this code for potential vulnerabilities"

​
Quick Query

gemini "How do I implement a simple HTTP server in Python?"
Gemini CLI defaults to the Google official API. By setting the OPENAI_API_BASE environment variable, it seamlessly switches to ePhone AI’s compatible interface.