GitHub's Copilot now picks the AI model for each coding task itself.
GitHub made Copilot Fusion available on all Copilot plans on Wednesday, after a preview called HydraFusion. It sends each task to one model, or lets one model draft while another checks the work. GitHub says its top setting scored within two points of Claude Code at about half the cost.
Why it mattersYou no longer have to guess which model fits a task, and you may spend less. You still pay each model's rate, so watch your bill on the highest setting.
Read in the app — free, in 9 languages
Related stories
Mistral gave away its trillion-parameter model, with one catch.2026-10-29Google's Gemini 4 Carbon edged past Claude on a hard AI ranking.
2026-10-29Experts went with their AI agent's hidden pick 86% of the time.
2026-10-28AI agents checked the longest proof in mathematics in 24 days.
2026-10-28Apple will let outside AI agents edit your Pages and Keynote files.
2026-10-27