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.

comments powered by Disqus

Featured

  • Hands On with GitHub Copilot App Technical Preview: Turning a Blazor Issue into a PR

    GitHub's brand-new Copilot desktop app, in technical preview, handled a small Blazor issue from planning through pull request creation, but the hands-on test also showed why developers still need to verify agent work in the running app before merging.

  • At Build 2026, Microsoft Sets Up Windows as an OS for AI Agents

    Microsoft's Build 2026 Windows developer announcements point to a broader platform strategy for agentic AI, spanning terminal workflows, local models, app-building skills, Cloud PCs and operating system-level containment.

  • Slammed by Copilot Usage-Based Billing on Day 1, Facing $180 Bill for June

    A journalist using GitHub Copilot Pro details how a broken editorial workflow on day one of usage-based billing led to runaway token consumption, a projected $180 monthly bill, and practical tactics for cutting AI credit burn.

  • AdaBoost.R2 Regression Using C#

    AdaBoost.R2 regression works by building an ensemble of decision trees, training them on reweighted data, and combining their predictions with a weighted median, while also showing how parameter choices affect accuracy and overfitting.

Subscribe on YouTube