Copilot Fusion

Copilot Fusion is a model router and orchestrator for GitHub Copilot. GitHub announced it at GitHub Universe 2026 on October 28, 2026, and it is generally available from day one. You no longer pick a specific model for each task. You pick "Copilot Fusion" in the model picker and an effort level, and Copilot decides which model or models to use and how they work together.

Changelog: Route and orchestrate models with GitHub Copilot Fusion · Docs: About GitHub Copilot Fusion

Key points

1. What it is: GitHub calls it "an intelligent runtime model router and orchestrator". It chooses models and execution patterns for each task and returns a single response. For example, one model can draft a solution while another reviews it.
2. Where it comes from: it combines Project HydraFusion's multi-model orchestration with Copilot's fine-tuned auto model selection, and it replaces the previous Auto model option.
3. Effort levels: Fusion Standard uses versatile models for everyday coding, Fusion High uses capable models for harder tasks and deeper reasoning, and Fusion Max uses the most capable models for the most demanding work. The docs also list a Fusion Fast level.
4. Execution patterns: depending on the task, it can answer with a single model, escalate a draft to a stronger model, or have one model write and another review.
5. Results: GitHub says Fusion Max scored within two points of Opus 5.5 Max on the Artificial Analysis Coding Agent Index, at half the cost and 40% less time per task.
6. Billing: each underlying model Fusion calls is billed at that model's standard rate. Through November 30, 2026, paid plans get 30% off model costs when using Fusion.
7. Policy-aware: it only uses models that your plan and your admin policies allow, including data-residency and FedRAMP restrictions. Fusion Standard may use some locally hosted models.

How to use it

1. Update your client. Fusion works in VS Code, the GitHub Copilot app, GitHub Copilot CLI and JetBrains IDEs, and GitHub says more clients are coming.
2. Open the model picker and choose Copilot Fusion.
3. Pick an effort level: Standard for routine edits and completions, High for tricky bugs and refactors, Max for the hardest multi-step tasks.

Tips

• Fusion is available on all Copilot plans, but some effort levels depend on your plan, so check the availability table in the docs.
• If none of the models Fusion uses are available to you (for example, because policies block them), Fusion won't appear in the picker.
• Use the 30% launch discount through Nov 30, 2026 to compare per-task cost against picking a single model by hand.