GitHub Makes Copilot Fusion Generally Available at Universe 2026

GitHub made Copilot Fusion, its multi-model routing and orchestration system, generally available on October 28, 2026, unveiling it at GitHub Universe 2026 alongside the new GitHub Copilot app, Copilot projects, and a deeper Copilot code review tier.

The announcements arrived in a Universe 2026 keynote post from Jay Parikh, Executive Vice President of CoreAI at Microsoft, whose teams include GitHub, and in a series of same-day changelog entries detailing availability, billing, and preview terms.

How Copilot Fusion Routes and Orchestrates Models

Selecting Copilot Fusion in the model picker chooses a routing and orchestration system rather than a specific model, according to the Copilot Fusion changelog. For each prompt, Fusion determines which models to use and how they work together, combining the multi-model orchestration of Project HydraFusion with the fine-tuned model selection behind Copilot’s auto model selection feature.

Users pick one of three effort levels. Fusion Standard prioritizes versatile models for everyday coding, Fusion High targets challenging tasks and deeper reasoning, and Fusion Max reserves the most capable models for the most demanding tasks and complex reasoning. For each task, Fusion runs one of three execution workflows: Single, where one model solves the task directly; Cascade, where an efficient model drafts a response and a quality check accepts it or escalates to a stronger model; and Critique, where one model drafts, a second model reviews, and the original model revises.

GitHub said 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 about 40% less time per task.

Administrators control which models Fusion can draw on through enterprise and organization model policies, and they can disable models for Fusion without disabling them for everyone. Enterprise managed settings can also set Fusion, at any effort level, as the default model for Copilot users.

Hari Pokhrel, a principal software engineer at AT&T, said in the changelog that Fusion Standard improved token efficiency across AT&T by automatically selecting the right model for each task, reducing unnecessary spend and preserving capacity for higher-value work, and that its decision-making has improved over time.

Fusion is billed per model at each model’s standard rate, and users on paid Copilot plans receive a limited-time 30% discount on model costs when using it. The system is available on all Copilot plans in Visual Studio Code, the GitHub Copilot app, GitHub Copilot CLI, and JetBrains IDEs, with additional client support to come. Developers who enabled auto, HydraFusion, or HydraFusion Max during the research preview will transition automatically to the corresponding Fusion effort levels.

The GitHub Copilot App and Copilot Projects

The GitHub Copilot app is designed for agentic software delivery, Parikh wrote, connecting agents and tools across projects and supporting work beyond code, including writing specs, presenting design discussions, and analyzing telemetry in one surface.

Copilot projects, available natively in the app starting October 28, 2026, let users run agent work across multiple repositories in fully managed, parallel sessions. The Copilot app changelog labels Copilot Projects a public preview: users describe a goal, attach context such as repositories, design mocks, or Slack threads, choose models and tools, and receive results such as pull requests for review. Project automations handle repeatable tasks, such as creating a promo video whenever a feature lands.

The app can also use context from connected tools such as Slack and Figma, and it can generate and edit images from natural language in chat. A computer-use feature, in public preview on macOS and Windows, lets Copilot read app content, click controls, enter or edit text, and navigate across desktop apps, including those without an API, command-line interface, or MCP integration. Copilot asks for approval before controlling an app, and organizations can disable the feature through managed settings.

Session continuity lets users start and follow the same cloud agent session across the GitHub app, VS Code, the CLI, and the web.

Code Review Max, Automations, and Enterprise Access

GitHub also introduced Copilot code review Max, which Parikh said posted the highest F1 score on ReviewBench for high-severity issues. The existing Lite and Balanced tiers remain for everyday reviews, with Max intended for changes that need a deeper look.

Copilot automations create AI-powered workflows inside a repository that run in the cloud, triggered manually, by events, or on a schedule, for tasks such as issue triage and code review. GitHub said automations can now learn from their outcomes and propose improvements for users to review and approve.

Starting October 28, 2026, GitHub Enterprise customers can use all Copilot features, including the Copilot app, code review, and automations, without buying a separate subscription, paying instead for the AI credits they use. The change is available immediately through GitHub Sales with self-serve coming soon; existing Copilot Business and Copilot Enterprise customers can keep their current plans or move over when ready.

The Road From HydraFusion and Infrastructure Additions

Fusion’s general availability follows the Project HydraFusion research preview GitHub introduced on September 4, 2026, after launching auto model selection earlier in the year. In offline evaluations reported with the preview, fixed HydraFusion policies improved verified task quality by 4.9 percentage points at 67% lower estimated cost than Claude Opus 5 on TerminalBench 2.1, came within 1.5 percentage points at 36% lower cost on DeepSWE, and came within 0.1 percentage points at 65% lower cost on CheckpointBench, GitHub’s internal benchmark built from real Copilot sessions. HydraFusion’s three execution patterns — Single, Cascade, and Critique — carry into Fusion’s workflow set.

GitHub said it has added 4 million CPU cores, 160 PB of high-speed storage, and 50 Tb/s of network capacity so far in 2026. Three principles guide its new Git architecture: simplify the primitives, decouple storage from compute, and minimize coordination. The company is migrating to a multi-region deployment in Azure and expects to complete that migration in early 2027.