gemini-cli/docs/cli/index.md

Gemini CLI

Within Gemini CLI, packages/cli is the frontend for users to send and receive prompts with the Gemini AI model and its associated tools. For a general overview of Gemini CLI, see the main documentation page.

Navigating this section

• Authentication: A guide to setting up authentication with Google's AI services.
• Commands: A reference for Gemini CLI commands (e.g., /help, /tools, /theme).
• Configuration: A guide to tailoring Gemini CLI behavior using configuration files.
• Enterprise: A guide to enterprise configuration.
• Token Caching: Optimize API costs through token caching.
• Themes: A guide to customizing the CLI's appearance with different themes.
• Tutorials: A tutorial showing how to use Gemini CLI to automate a development task.

Non-interactive mode

Gemini CLI can be run in a non-interactive mode, which is useful for scripting and automation. In this mode, you pipe input to the CLI, it executes the command, and then it exits.

The following example pipes a command to Gemini CLI from your terminal:

echo "What is fine tuning?" | gemini

Gemini CLI executes the command and prints the output to your terminal. Note that you can achieve the same behavior by using the --prompt or -p flag. For example:

gemini -p "What is fine tuning?"

For non-interactive usage with structured output, use the --output-format json flag for scripting and automation.

Get structured JSON output for scripting:

gemini -p "What is fine tuning?" --output-format json
# Output:
# {
#   "response": "Fine tuning is...",
#   "stats": {
#     "models": { "gemini-2.5-flash": { "tokens": {"total": 45} } }
#   },
#   "error": null
# }