GitHub Copilot adds cost and quality tiers for auto model selection
GitHub Copilot auto now offers efficiency, balance and intelligence tiers to guide how it weighs cost, quality and response time. All tiers use the same available models, and usage is billed according to the model auto selects.
SessionWatcher editorial · Published · Updated · Source announcement: 2026-09-14
Related guide: How to check your GitHub Copilot usage
Three ways to tune Copilot Auto
GitHub says Copilot auto model selection now offers efficiency, balance and intelligence tiers. Efficiency prioritizes keeping costs low for fast, straightforward tasks. Balance weighs cost, quality and latency together for everyday work. Intelligence prioritizes quality for complex tasks.
The tiers do not change the set of available models. GitHub says Auto evaluates each prompt individually, so a simple task may still use a small, efficient model even when intelligence is selected.
Sources: Configure cost and quality in Copilot auto model selection - GitHub Changelog
Usage follows the selected model
The feature is rolling out in Visual Studio Code, Copilot CLI and the GitHub Copilot app. Usage is charged based on the model Auto selects, regardless of the chosen tier. GitHub also says paid subscribers continue to receive a 10% discount on usage billed through Auto.
Sources: Configure cost and quality in Copilot auto model selection - GitHub Changelog
AI assisted reporting, checked against the linked official sources. Source pages checked 2026-10-03. Editorial process and corrections.