GitHub Copilot Fusion: pick an effort level instead of a model
Copilot decides which model to use for each task and can combine several. It’s available on all plans.
At Universe on October 28, GitHub made Copilot Fusion generally available. Instead of a specific model, you can now pick Fusion in the model menu, and Copilot decides which models to use for the task.
What’s new
Fusion combines Project HydraFusion’s multi-model orchestration with automatic model selection. There are three workflows:
- Single: one model completes the task;
- Cascade: an efficient model drafts, and a quality check accepts the draft or escalates to a stronger model;
- Critique: one model drafts, another reviews, and the first revises.
You only pick an effort level: Standard, High or Max.
According to GitHub, Fusion Max scored 60 on the Artificial Analysis Coding Agent Index, within two points of Claude Code with Opus 5.5 Max. It used about half the cost and tokens per task, and about 40% less time.
How to try it
Fusion is available on all Copilot plans in VS Code, the GitHub Copilot app, the CLI and JetBrains IDEs. If you enabled HydraFusion in the research preview, you’ll move to the matching level automatically.
Limitations
You’re billed for each model Fusion uses at its standard rate, so a multi-model task can cost more than expected. Paid plans get a 30% discount for a limited time. Fusion only uses models allowed by your organization’s policies.
Prepared with AI from public sources.