Home / Code / GitHub Copilot Fusion

GitHub Copilot Fusion
For hassle-free model choice when coding: automatically routes by task and orchestrates multiple models
What is GitHub Copilot Fusion
GitHub Copilot Fusion automatically routes coding tasks to suitable models and orchestrates multiple models, and it became generally available on 2026-10-28. Fusion Max scored 60 on the Artificial Analysis coding agent index. Copilot plans include Free, Pro ($10/month), and Pro+ ($39/month) among others; which plans include Fusion has not been verified.
How to use
- Update your client: Visual Studio Code, the GitHub Copilot app, GitHub Copilot CLI or a JetBrains IDE.
- Open the model picker and select Copilot Fusion.
- Choose an effort level: Fusion Standard (everyday coding), Fusion High (challenging tasks and deeper reasoning) or Fusion Max (most demanding tasks).
- Prompt as usual;
- for each prompt Copilot Fusion decides which models to use and how they work together (Single, Cascade or Critique workflows).
- Administrators can choose which models Copilot Fusion may use and set it, at any effort level, as the default model via Enterprise managed settings.
Use cases
- Letting Copilot automatically pick and orchestrate models for each coding task Balancing performance and cost without manually switching models Escalating from an efficient draft model to a stronger model only when needed Having one model critique and another revise answers Setting an org-wide default model policy for Copilot users
Price from official sources
Not stated
- Copilot Fusion is available on all Copilot plans.
- You are billed for each model it uses, at each model's standard rate;
- for a limited time, users on paid Copilot plans get a 30% discount on model costs when using Copilot Fusion.
- Copilot plans:Free $0 (limited chat and agent usage);
- Pro $10/month;
- Pro+ $39/month;
- Max $100/month.
Check the official site for current pricing · Price not yet checked by our editors
Source: github.com · Info as of Nov 2, 2026
Company
- Name
- GitHub, Inc.
Reviews
No reviews yet.
Alternatives
-
sweet-search
Free
For agents searching codebases: local semantic search that saves 5–33% per agent run
- Added
- Nov 2, 2026
Same category: Code
-
Skep Free For collaborating with coding agents across devices: share live sessions with a join code
- Added
- Nov 2, 2026
Same category: Code
-
Rufous
Free
For coding with small local models: an agent framework built for 2B–12B models
- Added
- Nov 2, 2026
Same category: Code
-
SKI
Freemium
For voice coding: drive multiple coding agents side by side
- Added
- Nov 2, 2026
Same category: Code
Social