Google Antigravity Rolls Out Orchestrator for Dynamic Model Handoffs

Google Antigravity said on November 12, 2026, that Orchestrator, a model-dropdown option rolling out for Google AI Ultra subscribers, reached near-Carbon task success on Terminal-Bench 4.1 while averaging 24% lower quota use and 19% faster completion by dynamically switching between Gemini 4 Carbon and Gemini 4 Hydrogen within one session.

The new Hydrogen model is rolling out separately in Antigravity to paid Google AI Pro and Ultra subscribers, while enterprises can access both models through Gemini for business. Google says additional models and subscription plans will be supported for Orchestrator in the future, and describes Hydrogen as the rapid-execution counterpart to Carbon and Argon’s deeper, long-horizon reasoning.

Dynamic Model Handoffs in One Session

Orchestrator targets routine feature development and debugging, where relying on a frontier reasoning model and multiple parallel agents throughout a session can make iteration slower and consume frontier quota. A conventional static router instead estimates difficulty from the opening prompt, then commits the entire task to the cheapest model it deems sufficient. Google says this one-time allocation fits long-running agents poorly because a task’s demands can change and only become clear during execution.

Orchestrator can move in either direction between the two models as a trajectory develops. In Google’s example, Carbon begins with read-only investigation of dependencies, resolves ambiguities and produces a plan containing explicit conditions that would trigger re-planning. Hydrogen then implements edits, updates packages and runs tests. If Hydrogen meets friction, Carbon takes back control to inspect the current state, fix the plan and continue execution. A session can therefore call on deeper reasoning for planning or recovery without assigning every implementation step to the same model.

Explicit Model Roles Through the SDK

Developers that want explicit assignments rather than automatic switching can connect Hydrogen and Carbon through the Antigravity SDK. This gives them programmatic control over which model handles each role in a multi-agent workflow.

In Google’s open-source issue-triage demonstration, Hydrogen agents handle incoming issue volume by triaging and coding, searching the codebase, asking clarifying questions and iterating on user-interface changes from pull-request comments. A Carbon agent is assigned larger refactors, new features and security checks. The demonstration uses the same broad division between rapid execution and deeper reasoning, but the developer defines the boundaries instead of delegating them to Orchestrator.

How Orchestrator Differs From /Swarm

Orchestrator follows the November 10, 2026 preview of Gemini 4 Carbon and /swarm, which targeted engineering work spread across many files and test suites. According to the /swarm documentation, a coordinator can split a task among named workers handling separate files, packages or questions, while verifiers review diffs and run tests; workers can also receive isolated working copies of a repository. Orchestrator addresses a different structure: it changes the model used during one evolving session rather than creating a team to work on independent pieces in parallel.

Together, the features divide agentic work in two different ways: across agents when a project can be partitioned, and across models when one conversation moves between planning, execution and repair. The practical shift is that model choice no longer has to be a single decision at the prompt; it can become part of the workflow’s architecture, either adaptive under Orchestrator or explicitly assigned through the SDK.