GitHub Copilot Chat adds auto model selection for all users
GitHub Copilot Chat now offers auto model selection for all users on github.com and the mobile app, allowing it to dynamically choose models based on request complexity and availability. This feature aims to optimize token usage and response quality, benefiting all Copilot plan subscribers. Auto mode routes to various models including Claude Sonnet 4.6, GPT-5.4 mini, GPT-5.4, and Haiku 4.5, with usage billed at a 10% discount.
- →Copilot Chat auto model selection now generally available
- →Auto mode dynamically routes to optimal models
- →Transparency and control features in auto mode
Features (1) ›
- Copilot Chat auto model selection now generally available
GitHub Copilot Chat's auto model selection is now generally available for all Copilot plans on github.com and the GitHub mobile app. This feature dynamically selects models based on request complexity and availability to optimize token use and quality.
Enhancements (1) ›
- Auto mode dynamically routes to optimal models
The auto model selection routes requests to models like Claude Sonnet 4.6, GPT-5.4 mini, GPT-5.4, and Haiku 4.5 based on real-time availability and task complexity. This routing respects user and administrator policies and is billed at a 10% discount for paid subscribers.
Notes (1) ›
- Transparency and control features in auto mode
Users can see which model was used by hovering over the response and can switch between auto mode and specific models on a per-response basis. Auto mode evaluates tasks to choose the optimal model based on complexity and system health.
https://github.blog/changelog/2026-06-17-auto-mode-in-copilot-chat-available-for-all-users