Gemini CLI Integration

Overview

Gemini CLI is Google's open-source coding agent that edits files and runs commands straight from your terminal. Set UnoRouter as its base URL and you reach Gemini, Claude, GPT, and every other model through one OpenAI-compatible key instead of a Google-only account.

Quick Config

Drop these values into the client. Your key auto-fills when you are signed in.

Base URL: https://api.unorouter.com
API Key: YOUR_API_KEY

Compatibility

Step-by-step setup

1. 1
   Install Gemini CLI

   Install the Gemini CLI globally with npm. On Windows, run this inside WSL.

   bash

   npm install -g @google/gemini-cli

   Sign in to auto-fill your API key

2. 2
   Set environment variables

   Create `~/.gemini/.env` with your UnoRouter API key and set `GOOGLE_GEMINI_BASE_URL` to UnoRouter's bare base URL. The Gemini SDK appends its own path, so do not add `/v1`.

   bash

   # ~/.gemini/.env
   GEMINI_API_KEY=YOUR_API_KEY
   GOOGLE_GEMINI_BASE_URL=https://api.unorouter.com

   Sign in to auto-fill your API key

3. 3
   Launch Gemini

   Run `gemini` in your project directory to start the session.

   bash

   gemini

   Sign in to auto-fill your API key

$env:GEMINI_API_KEY="YOUR_API_KEY"
$env:GOOGLE_GEMINI_BASE_URL="https://api.unorouter.com"

gemini

Recommended models

Free models that work well here. Paste any model id into the client.

Gotchas

• !If requests 404, you added a path to the base URL. `GOOGLE_GEMINI_BASE_URL` must be the bare host with no `/v1` suffix; the SDK appends the rest.
• !If authentication fails, confirm `GEMINI_API_KEY` in `~/.gemini/.env` is your UnoRouter key and the file is read by your shell session.