GitHub Copilot Fusion is GA: choose an effort level, let Copilot pick and combine the models
What is it?
Copilot Fusion shows up in the model picker, but it isn't a model. You choose an effort level (Standard, High or Max) and Fusion decides, prompt by prompt, which models to run and how. It has three patterns: Single, where one model answers directly; Cascade, where a cheaper model drafts and a quality check decides whether to escalate; and Critique, where a second model reviews and the first revises. It merges the Project HydraFusion research preview with Copilot's auto model selection.
Why does it matter?
It cuts the waste of developers picking a premium model for a hard task and forgetting to switch back. GitHub says Fusion Max scored 60 on the Artificial Analysis Coding Agent Index, within two points of Claude Code running Opus 5.5 MaxVendor claim, at about half the average API cost per task and roughly 40% less timeVendor claim. Admins can limit which models Fusion may use, or make it the default, which helps control spend across an organization.
Maturity
GAGenerally available on all Copilot plans in VS Code, the Copilot app, Copilot CLI and JetBrains IDEs. Each model is billed at its standard rate, and paid plans get 30% off for a limited time.
How to track it
- Discount: check GitHub's billing docs for when the 30% discount ends.
- Independent numbers: see whether Artificial Analysis publishes Fusion's results on its Coding Agent Index.
- Local models: follow the same-day changelog on selecting local models in Fusion to see how far that support extends.