Gemini CLI
Gemini CLI is an open-source command-line tool for AI-assisted coding, built by Google (released 2025-06). Gemini CLI's verified model list is still being expanded, so this page emphasizes runtime shape, pricing, and comparable AI coding harnesses. It's free and open source. Engineers run it from a terminal, where it can inspect repositories, edit files, call tools, and drive repeatable agentic coding workflows across local projects.
Overview
Google open-source command-line AI agent that uses a ReAct loop, local tools, and MCP servers to fix bugs, create features, improve tests, and handle developer workflows.
Compare Gemini CLI side-by-side with other CLI, IDE, cloud, and framework agents on pricing, model coverage, and release cadence.
Best LLMs for this agent
Pricing and Provider Comparison
Hosted agents expose plan pricing. Bring-your-own-key agents pass the main cost through the model provider route you configure.
Featured Model Specs
Model Compatibility Matrix
Underlying Models
Compare to Similar Harnesses
FAQ
What is Gemini CLI?
Gemini CLI is an open-source command-line tool for AI-assisted coding, built by Google (released 2025-06). Engineers run it from a terminal, where it can inspect repositories, edit files, call tools, and drive repeatable agentic coding workflows across local projects. It is primarily used for agentic coding from a local shell.
How much does Gemini CLI cost?
Gemini CLI is free and open source. You pay only for the underlying model API usage.
Is Gemini CLI open source?
Yes, Gemini CLI is open-source software.
What are alternatives to Gemini CLI?
Alternatives include MiMo-Code, Mistral Vibe, and OpenAI Codex CLI.
When was Gemini CLI released?
Gemini CLI was released in 2025-06.