CubenceCubenceDocs

Updated:

Gemini CLI FAQ

Here are common questions and solutions when using Gemini CLI.

For help, choose a channel under pre-sales and after-sales support.

Base URL and routes

The examples use the Mainland China route, https://api-lb.cubence.ai. For global use, set the Base URL to https://api.cubence.ai; outside Mainland China, you can use https://api.cubence.com. Keep any request path when switching routes. See API endpoints and Base URL configuration.

Usage Tips

What to do if Gemini CLI usage experience is poor?

Gemini CLI currently has some usage issues, such as inability to properly call models or paste images. If you encounter problems, suggestions:

  1. Use third-party VSCode extensions like Roo Code as an alternative
  2. If using Roo Code, select OpenAI Response request format
Which Gemini models are supported?

Cubence supports these Gemini models:

  • gemini-3-pro-preview
  • gemini-2.5-pro
  • gemini-3-flash-preview

For specific available models, check the model list in Cubence console.

Configuration Issues

What to do if model doesn't exist error appears?
  1. Check if GEMINI_MODEL in .env file is correct
  2. Confirm model name is spelled correctly
  3. Confirm the model is available in Cubence console
What to do if no available channel error appears?
  1. Check if API Key is correct
  2. Confirm account balance is sufficient
  3. Check if GOOGLE_GEMINI_BASE_URL is set correctly
What to do if API Key configuration doesn't take effect?
  1. Confirm .env file is in the correct location (~/.gemini/.env)
  2. Confirm selectedType in settings.json is set to gemini-api-key
  3. Restart the terminal and try again

Other Issues

What to do if Gemini model doesn't have internet access?

Gemini models typically don't have built-in internet capabilities. If you need internet access:

  1. Use MCP tools to extend internet capabilities
  2. Manually copy web content into the conversation
What to do about connection timeout?
  1. Check if network connection is normal
  2. Confirm GOOGLE_GEMINI_BASE_URL matches the root URL of your selected route, such as https://api-lb.cubence.ai for Mainland China
  3. If using a proxy, ensure proxy configuration is correct