Google launches Gemini API CLI for AI coding agents and scripts
Overview
Google has released the Gemini API CLI, a command-line tool that lets existing AI agents call the Gemini API. Philipp Schmid announced the launch on X, saying the tool is not a new coding agent and works with agents including Claude Code, Codex, and Antigravity.
He lists Cursor, OpenClaw, and Hermes as further agents it can be given to.
The Gemini API Changelog describes the release as a beta, a stateless, zero-dependency client for AI coding agents, scripts, and CI pipelines, invoked as gemini-api. It uses the Interactions API to generate text and media, analyze files, and run Gemini managed agents. Schmid says it can also transcribe recordings and run Deep Research in the background.
Written by AI from the articles below · updated Oct 27, 10:49 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Gemini API ChangelogOfficialGoogle releases Gemini API CLI beta for coding agents and CI pipelines
AIGoogle released the Gemini API CLI (gemini-api) in beta, a stateless, zero-dependency command-line client for AI coding agents, scripts, and CI pipelines. The tool uses the Interactions API to generate text and media, analyze files, and run Gemini managed agents.
Philipp Schmid@_philschmidOfficialGoogle launches Gemini API CLI for calling Gemini from existing AI agentsAIPhilipp Schmid says Google has launched the Gemini API CLI, a command-line tool for calling the Gemini API. It can be used from agents such as Claude Code, Codex, and Antigravity, and is not a new coding agent. It can generate images, video, speech, and music, analyze PDFs and other media, transcribe recordings, and run Deep Research in the background.

Heat Trend
- Current comparable heat
- 4
- Peak comparable heat
- 10Oct 27, 12:00 AM ET
- Change in past 24 hours
- -50%
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.