Configure cost and quality in Copilot auto model selection
Copilot's auto model selection adds efficiency, balance, and intelligence tiers, rolling out in VS Code, Copilot CLI, and the Copilot app.
GitHub Copilot's auto model selection now lets users choose from three tiers that control how it weighs cost, quality, and response time when picking a model for each prompt. Efficiency prioritizes low cost for fast, straightforward tasks; Balance weighs cost, quality, and latency together for everyday work; Intelligence prioritizes quality for complex tasks. All three tiers draw on the same set of available models, and auto still evaluates each prompt individually, so a simple task like adding a docstring may still use a small, efficient model even under the Intelligence tier.
The feature is rolling out in Visual Studio Code, Copilot CLI, and the GitHub Copilot app. Usage is charged based on whichever model auto selects, regardless of tier, and paid subscribers keep their 10% discount on usage billed through auto.
