GoogleapiGemini API CLI (Beta)
A free, open-source command-line tool for calling Gemini models and Google's managed agents from a terminal. For developers and for AI coding agents that run shell commands.
Details
- One command line tool covers creating (image, speech, music, video, text), understanding (PDFs, images, audio, video, YouTube links), and transcription
- Runs Google's managed agents, such as the Deep Research agent and the Antigravity agent, including in the background with a job ID you check later
- Media commands save the file to disk and print only the path, and results can come back as JSON, so an AI agent can use the output without extra parsing
- Installs with a one-line script on Mac, Linux, or Windows and needs a Gemini API key. You pay normal Gemini API rates for what you call
- Beta: Google says commands can change between minor versions, so pin a version in anything automated
Best for
Generating images, speech, video, or text, or running a Deep Research agent, from a script without writing SDK code.
When to use it
You already work with a coding agent like Claude Code or Codex and want it to call Gemini as one more tool.
Who benefits
Technical marketers and ops people who automate content or research jobs with scripts.
Join the newsletter to get ahead with AI.
I share strategies, new modules, free guides, and tools to get you better at using AI in your work.
Leading a team? See team programs →