GitHub Copilot Fusion, which routes and orchestrates models for each task, is generally available

GitHub says Copilot Fusion is generally available. Instead of choosing a model, a user picks Copilot Fusion in the model picker and an effort level (Standard, High or Max); Copilot decides which models to use and how they work together. It combines the multi-model orchestration of the earlier Project HydraFusion preview with Copilot's auto model selection. Workflows include a single model, a cascade (an efficient model drafts and a quality check decides whether to escalate) and critique (one model drafts, another reviews, the first revises).

GitHub's own claim: on the Artificial Analysis Coding Agent Index, Copilot Fusion Max scored 60, within two points of Claude Code with Opus 5.5 Max, at about half the average API cost per task, about half the tokens and about 40% less time per task.

Artificial Analysis, which runs the index, published its own run of Fusion's Max setting in Copilot CLI (Coding Agent Index v2.0). It reports $5.59 per task against $11.42 for Claude Code with Opus 5.5 (max), and 7.2M tokens per task, about half of Claude Code's. By its figures Fusion leads Terminal-Bench 4.0 with 71, ranks third on FrontierCode with 51 (Claude Code with Opus 5.5 scores 56) and scores 57 on SWE-Atlas-QnA-AA. It lists Claude Opus 5.5, Claude Sonnet 5.5, GPT-6 Astra and GPT-6 Sol among the models Fusion chooses between, and notes that token costs are charged by the underlying models used.

• Availability: all Copilot plans, in Visual Studio Code, the GitHub Copilot app, Copilot CLI and JetBrains IDEs; more clients are coming. Research-preview users of auto, HydraFusion or HydraFusion Max move to the matching Fusion effort level.
• Billing: each model Fusion uses is billed at its standard rate. For a limited time, paid plans get 30% off model costs when using Fusion.
• Administrators: Fusion uses only models enabled in enterprise and organization policies; admins can disable individual models for Fusion and set Fusion, at any effort level, as the default model through enterprise managed settings.