GitHub Copilot CLI now supports auto model selection as a generally available feature for all Copilot plans. With auto mode, Copilot dynamically routes requests to the most efficient model (such as GPT-5.4, GPT-5.3-Codex, Sonnet 4.6, or Haiku 4.5) based on your plan and policies, helping mitigate rate limits. Users retain transparency by seeing which model was used and can switch between auto and specific models at any time. Billing is based on the selected model's multiplier, and paid subscribers receive a 10% discount on the multiplier when using auto.
Sort: