News
GitHub Copilot Adds 'Auto Model' Selection Preview for Smarter, Faster Responses
Microsoft today announced a new preview feature for Copilot Chat in Visual Studio called auto model selection, designed to automatically choose the optimal AI model for each chat request based on real-time capacity and performance. The feature delivers faster responses, reduces the likelihood of rate limiting, and offers paid users a 10% discount on premium requests.
With auto enabled, users no longer need to manually select models, Microsoft and GitHub announced in a co-authored post on Microsoft's DevBlogs site. Copilot will automatically choose from a range of available options, including GPT-5, GPT-5 mini, GPT-4.1, Claude Sonnet 4.5, and Haiku 4.5, depending on availability and organizational settings. Once selected, the chosen model remains consistent for the duration of a chat session.
Currently, Claude Sonnet 4.5 primarily powers auto for paid users. Visual Studio applies a variable model multiplier to track usage, with Sonnet 4.5 requests counting as 0.9x of a premium request. If paid users exhaust their premium allotment, auto automatically switches to a 0x model--such as GPT-4.1--ensuring uninterrupted access.
Microsoft plans to expand auto's capabilities by dynamically switching between smaller and larger models based on task complexity, adding more language models, extending access to free-tier users, and improving model visibility in the selection dropdown. Auto model selection is currently rolling out in preview to all Copilot Chat users in Visual Studio.
About the Author
David Ramel is an editor and writer at Converge 360.