Feature Overview

GitHub Copilot auto model selection is now generally available in JetBrains IDEs for all Copilot plans. This intelligent routing system automatically selects an appropriate model on your behalf based on real-time availability and performance metrics, eliminating the need to manually choose between specific models.

How Auto Model Selection Works

The auto feature dynamically routes requests to high-quality models including GPT-5.4, GPT-5.3-Codex, Sonnet 4.6, and Haiku 4.5—with the available models changing over time based on your plan and organization policies. Key capabilities include:

• Visibility: Hover over any model response to see which model was used
• Flexibility: Switch between auto and any specific model at any time
• Policy compliance: Auto respects all administrator model settings and restrictions

Billing & Cost Savings

Premium request use for auto is billed according to the model selected. Currently, auto is limited to models with 0x to 1x cost multipliers. All paid subscribers receive a 10% discount on the model multiplier when using auto—for example, selecting a 1x model costs 0.9 premium requests instead of 1.

Future Enhancements

GitHub plans to make auto even more intelligent by adding task-aware selection. The system will eventually match models to the complexity level of your specific request, ensuring optimal performance and cost efficiency for different coding tasks.