Copilot Fusion GA picks models for you

What changed

Copilot Fusion turns model-picking into one choice. Select Fusion, pick an effort level, and Copilot routes models per prompt.

When you select Copilot Fusion, you aren’t picking a specific model. For each prompt it decides which models to use and how they work together — including Single, Cascade (draft then escalate) and Critique (draft, review, revise).

You only pick the effort level: Standard for everyday coding, High for tougher reasoning, Max for the hardest jobs.

GitHub says Copilot Fusion Max scored 60 on the Artificial Analysis Coding Agent Index, within two points of Claude Code with Opus 5.5 Max, at about half the average API cost per task, using about half as many tokens and taking about 40% less time per task.

Billing

You’re billed for each model Fusion uses, at each model’s standard rate. GitHub says users on paid Copilot plans get a 30% discount on model costs when using Copilot Fusion through Nov 30, 2026 (GitHub Docs: Optimizing your AI usage).

Who can use it

All Copilot plans, in Visual Studio Code, the GitHub Copilot app, GitHub Copilot CLI and JetBrains IDEs. Admins control which models Fusion may use and can set Fusion as the default. Prior auto, HydraFusion or HydraFusion Max selections move to the matching Fusion effort levels.

What to do

Update your client, open the model picker, select Copilot Fusion and choose an effort level.