The short version

Google announced Gemini 4 Hydrogen on November 12, expanding its AI model family with a lower-cost system designed for coding, Search and agentic workflows, according to the company's official product release.

Google introduces a new AI option

Google DeepMind says Gemini 4 Hydrogen is designed for rapid everyday coding, multimodal document analysis and tool-based workflows. The company is bringing it to Google AI Studio, the Gemini API, Google Search, the Gemini app and selected business subscriptions. Its advertised developer prices are US$1.50 per million input tokens and US$7.50 per million output tokens. Prices, eligibility and feature availability depend on service and account details.

Performance claims come from Google's testing

The company says Hydrogen can complete some work faster than its other Gemini 4 models and that its new Antigravity Orchestrator can switch between models to reduce resource use. Reported benchmark scores and safety improvements are provider claims under defined test conditions, not independent evidence that the system is always more accurate or suitable for critical decisions. Real-life users should still verify generated facts, software and code.

Search experience may change for publishers and readers

Google says the Search rollout is intended to better interpret complex, multi-part queries and produce more visual answers. For Canadian publishers, shifts in search presentation could change how traffic reaches independent news websites, though the effect requires measurement. CDN News will distinguish a launched feature from its actual influence on rankings or website visits.

Follow the evidence

Sources & transparency

Google — Introducing Gemini 4 HydrogenGoogle — Gemini 4 Hydrogen in Search

Original CDN News coverage. Sources are linked for reference.

Source linked ·

Request a correction