GitHub Copilot auto model selection now offers three tiers: efficiency, balance, and intelligence. Choose the tier that reflects how you want auto to weigh cost, quality, and response time for each prompt. Copilot will then optimize accordingly.
- Efficiency prioritizes keeping costs low and suits fast, straightforward tasks.
- Balance weighs cost, quality, and latency together, and is a good fit for everyday work.
- Intelligence prioritizes quality and is built for complex tasks.
All three tiers use the same set of available models. Auto individually evaluates each prompt to select a best-suited model. For example, a simple task like adding a docstring to an existing function may use a small, efficient model even when auto is optimizing for intelligence.
This feature is currently rolling out in Visual Studio Code, Copilot CLI, and GitHub Copilot app. Usage is charged based on the model auto selects, regardless of tier. Paid subscribers continue to receive a 10% discount on usage billed through auto.
This is the first step in our journey toward letting you customize how model selection works for you, with more visibility into the tradeoffs you’re making.
Learn more about Copilot Auto model selection, along with the updated selection of models available.