Starting today, developers can build with Gemini 4 Hydrogen, bringing cutting-edge intelligence to everyone — with speed and efficiency for everyday coding and agentic workflows. Built for rapid iteration, Hydrogen handles repository coding and debugging, interactive web development, and multimodal workflows — running standalone across four configurable thinking levels or alongside frontier models like Gemini 4 Carbon and Gemini 4 Argon. With tighter instruction following and fewer fabricated claims, it helps you ship cleaner, production-ready code faster.
Start building with the Gemini API in Google AI Studio and Android Studio, Gemini for business, or, if you are a paid Google AI Pro or Ultra subscriber, try it in Google Antigravity.
- Check out the [Gemini API What’s New Guide](https://aistudio.google.com/docs/whats-new-gemini-4-hydrogen) for model details, setup instructions, and thinking-level controls.
- Read the [Google Antigravity blog](https://antigravity.google/blog/gemini-4-hydrogen-in-google-antigravity) to see how new features like Orchestrator pair Hydrogen with Gemini 4 Carbon.
source & further reading
blog.google — original article
Gemini 4 Hydrogen
Gemini Decisions API: Fast, calibrated multimodal decisions
The Multimodal Knowledge Agent Benchmark