Auto mode in Copilot Chat available for all users

GitHub Copilot auto model selection is now generally available in Copilot Chat on github.com and the GitHub mobile app for all Copilot plans. With auto, Copilot chooses a model on your behalf based on the complexity of your request and current model availability. Using auto allows you to better optimize for token use while maintaining high quality results.

How it works

Auto model selection is dynamic, routing to models based on real-time availability and the complexity of your request. It provides you with the same access to your favorite models while optimizing for cost and response quality. Auto routes to models like Claude Sonnet 4.6, GPT-5.4 mini, GPT-5.4, and Haiku 4.5 based on your plan and policies. The models auto will route to will change over time.

Benefits of auto mode

• Transparency: You can see which model was used by hovering over the model response.
• Task-based routing: Auto evaluates your task and chooses the optimal model based on complexity and real-time system health.
• Stay in control: You can switch between auto and any specific model of choice on a per-response basis.
• Respects your policies: Auto honors all user and administrator model settings.

Token use

Use of auto is billed at a 10% discount for all paid subscribers.