Configure Copilot auto model selection tiers
Choose efficiency, balance, or intelligence to balance cost, quality, and response time.
Auto model selection tiers
Where
Copilot settings
Why
To optimize Copilot's model choice based on your priorities for cost, quality, and speed for each prompt.
What it does and when to use it
GitHub Copilot's auto model selection now allows users to choose between three tiers: efficiency, balance, and intelligence. This setting lets you dictate how the system weighs cost, quality, and response time for each individual prompt, enabling Copilot to optimize its model selection accordingly.
Sources and credit
- Configure cost and quality in Copilot auto model selection ↗GitHub · GitHub Changelog: Copilot · Sep 14, 2026 · paraphrased
First seen on Subvolts Sep 14, 2026. Updated Sep 14, 2026. Spotted a problem? Tell us.
Where it shows up
- Configure cost and quality in Copilot auto model selectionMicrosoft · GitHub Changelog: Copilot · Sep 14, 2026
Terms used
Related in the PlaybookPlaybook →
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- Eval methodEvaluating AI model upgrades for cost and qualityMeasure token consumption and output quality on specific tasks before adopting new AI models. · 120 min
- PromptGenerate a flashcard web application with specific featuresCreate a flashcard app with features for creation, search, review, and statistics. · 15 min
- Eval methodEvaluate AI models on your specific tasks, not just public benchmarksTest AI models using your own repositories and agent setup to get accurate performance results for your team's workflow. · 60 min
- HeuristicChoose the minimal viable model for your work, not the smartestSelect the least expensive AI model that meets your specific task requirements to optimize cost and performance. · 15 min
- HeuristicSelectivity is key to multi-model orchestrationChoose the least complex workflow that meets quality needs, using more powerful models only when necessary. · 5 min
- Setting tipEnable HydraFusion and HydraFusion Max in CopilotAccess advanced AI model orchestration in VS Code, GitHub Copilot app, and CLI. · 2 min
Questions people ask
- Which AI tools does this work with?
- The sources used it with Copilot.
- Where did this come from?
- GitHub (GitHub Changelog: Copilot). Subvolts collected, normalized and credited it; the link above opens the original.