Hydrogen gives you four thinking levels (low, medium, high, and a new xhigh tier) that scale intelligence, latency, and token use in a predictable progression — so you only wait and pay for the reasoning depth a task needs.

And with Orchestrator in @Antigravity (available to Google AI Ultra subscribers), multi-model teamwork happens automatically in a single session:

Carbon sets the architectural plan, hands off code edits and testing to Hydrogen, and steps back in if a check fails, reaching near-Carbon task success rates on Terminal-Bench 4.0 while consuming 24% less quota and completing 19% faster on average.