Gemini CLI

Overview

Gemini CLI is Google’s open-source command-line AI tool that lets you interact with Gemini models directly from the terminal for code understanding, generation, and editing. By connecting Gemini CLI to AihubMax, you can use AihubMax’s Gemini model offerings.

Gemini CLI does not support custom base URLs through configuration files. Configuration requires modifying source files inside the installed package. This modification needs to be reapplied after package updates.

Prerequisites

AihubMax API Key

An active AihubMax API key with access to Gemini models. Go to AihubMax →

Node.js 20+

Node.js v20 or later and npm are required for installing Gemini CLI. Download Node.js →

Installation & Configuration

Step 1: Install Gemini CLI

npm install -g @google/gemini-cli

Step 2: Set Your API Key

Before configuring environment variables, go to the AihubMax Console to create a dedicated key:

Open the “API Keys” page and click “Create Key”.
Name the key “Gemini CLI” or another easily identifiable name.
Make sure to select the “Gemini_CLI” group — this group enables the additional transcoding and rate limits required by the Gemini protocol.

If you don’t select the “Gemini_CLI” group, Gemini CLI may not be able to call AihubMax’s Gemini models properly, or you may encounter 403/429 errors.

After generating the key, set it as the GEMINI_API_KEY environment variable. Choose either method below: use CC-Switch for automatic injection, or manually export the variable in your shell profile.

CC-Switch (Recommended)
macOS / Linux
Windows PowerShell

Download and install the package matching your system from GitHub Releases.
In CC-Switch, add a new “Gemini CLI” configuration. Keep the default Base URL as https://api.aihubmax.com, and select “Custom Header” for the authentication method.
Go back to the AihubMax key list, click “Import to CCS” next to your target key, and select the configuration you just created.

One-click import of Gemini CLI configuration from AihubMax

After launching a terminal through CC-Switch, the tool will automatically inject GEMINI_API_KEY into the current shell — no manual export needed.

export GEMINI_API_KEY="sk-your-foxapi-api-key"

Then reload your shell configuration:

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

[Environment]::SetEnvironmentVariable("GEMINI_API_KEY", "sk-your-foxapi-api-key", "User")

Restart PowerShell after setting the variable.

Step 3: Modify the Base URL

CC-Switch only injects GEMINI_API_KEY — it does not modify the Base URL configuration inside the CLI installation directory. Regardless of which method you chose in the previous step, the following modification must be performed once.

Gemini CLI does not support custom base URLs through configuration. You need to modify two source files inside the installed package.First, find your npm global installation directory:

npm root -g

If you’ve cloned this docs repository, you can also run the bundled helper script to patch both files automatically:

bash 101.api_docs/mintlify/ai-tools/patch-gemini-cli-base-url.sh

The script resolves the global install directory, patches both index.mjs and index.cjs, and creates .foxapi.bak backups of the original files.Then modify the following two files:File 1: {install_dir}/@google/gemini-cli/node_modules/@google/genai/dist/node/index.mjs (around line ~11222)File 2: {install_dir}/@google/gemini-cli/node_modules/@google/genai/dist/node/index.cjs (around line ~11244)In both files, find and replace:

// Before:
initHttpOptions.baseUrl = `https://generativelanguage.googleapis.com/`;

// After:
initHttpOptions.baseUrl = `https://api.aihubmax.com/`;

On macOS/Linux, you can use sed for quick replacement:

INSTALL_DIR=$(npm root -g)
sed -i.bak 's|https://generativelanguage.googleapis.com/|https://api.aihubmax.com/|g' \
  "$INSTALL_DIR/@google/gemini-cli/node_modules/@google/genai/dist/node/index.mjs" \
  "$INSTALL_DIR/@google/gemini-cli/node_modules/@google/genai/dist/node/index.cjs"

After updating Gemini CLI (npm update -g @google/gemini-cli), the source files will be overwritten. You will need to re-apply this modification.

Step 4: Start Using Gemini CLI

Launch Gemini CLI in your project directory:

cd /path/to/your/project
gemini

Or run a one-off command:

gemini "Explain the structure of this project"

To switch models in interactive mode, type /model.

Verify the Connection

Run a test command to confirm everything is working:

gemini "Hello, please confirm you are working properly."

A successful response confirms that Gemini CLI is correctly routing through AihubMax.

Available Models

Model	Description
`gemini-2.5-pro`	Most capable Gemini model for complex tasks
`gemini-2.5-flash`	Fast and efficient for everyday coding tasks
`gemini-3-pro-preview`	Next-gen Gemini Pro preview
`gemini-3-flash-preview`	Next-gen Gemini Flash preview

Troubleshooting

Authentication error

Verify your GEMINI_API_KEY environment variable is set correctly, with a value that is your AihubMax API Key (starts with sk-).
Ensure the key has not expired and has sufficient balance.
Verify the key has access to Gemini models.

Connection timeout or errors

Verify the base URL modification was applied correctly in both files (index.mjs and index.cjs).
Check your network connection to api.aihubmax.com.
Try using a VPN if your region has connectivity issues.

Changes lost after update

After running npm update -g @google/gemini-cli, the source files are overwritten.
Re-apply the base URL modification following Step 3 above.

Model not available

Confirm the model name matches the AihubMax model list.
Use /model in interactive mode to switch between available models.

MCP Servers

AI Coding Toolbox

Agents

Overview

Prerequisites

AihubMax API Key

Node.js 20+

Installation & Configuration

Verify the Connection

Available Models

Troubleshooting

​Overview

​Prerequisites

AihubMax API Key

Node.js 20+

​Installation & Configuration

​Verify the Connection

​Available Models

​Troubleshooting

Overview

Prerequisites

Installation & Configuration

Verify the Connection

Available Models

Troubleshooting