Different software engineering problems require different model strengths. While a quick lint fix or unit-test classification doesn’t warrant a heavy reasoning frontier model, refactoring a legacy service across thirty files definitely does.
Anthropic’s Claude Opus 5.5 and Claude Sonnet 5.5 are now officially available in Google Antigravity (across Antigravity 2.0 Desktop, the CLI, and IDE extensions for VS Code, JetBrains, and Visual Studio).
Here is a breakdown of what this means:
What’s New?
- Claude Opus 5.5: Built for heavy-lift reasoning, complex multi-file architectural refactoring, and multi-turn planning.
- Claude Sonnet 5.5: Fast, high-efficiency, lower-cost complement for day-to-day coding and iterative feature delivery.
-
Dynamic Intra-Session Switching: Switch models mid-session via the dropdown or
/model claude-opus-5-5in the CLI without losing context, open terminal states, or workspace artifacts. - Unified Governance: Single enterprise billing through Google Cloud with standard security controls (sandbox policies, MCP server boundaries, and URL allowlists).
How to Enable It
For Cloud Admins: In Google Cloud Console, navigate to Gemini Enterprise > Settings > AI developer tools. Under Antigravity authorized models, toggle on Claude Opus 5.5 and Sonnet 5.5 and configure monthly project spend limits.
For Developers: Update to the latest Antigravity release (Antigravity 2.0, CLI, or IDE extension) and select Claude from the model picker or via /model in your terminal.
