Noesion Radarnoesion.ai
Release2026-09-14

GitHub Copilot auto model selection now offers three tiers. Efficiency prioritizes low cost for fast tasks. Balance weighs cost, quality, and latency together. Intelligence prioritizes quality for complex tasks. All tiers use the same models. Auto evaluates each prompt to select the best model. Usage is charged by the selected model. Paid subscribers get a 10% discount on auto-billed usage. The rollout is ongoing. This is the first step toward customizable model selection.

What changed

Copilot auto model selection used a single default balance of cost, quality, and latency.

What it unlocks

Choosing how Copilot weighs cost, quality, and response time for each prompt.

What you need to act on it

  • a paid Copilot subscription
  • Visual Studio Code, Copilot CLI, or GitHub Copilot app

Sources

Send this to someone who needs it

Shares the story and its sources. Nothing about you.

What does this mean for your job?

This is the story as everyone gets it. Once a week we send you the version written for your role — what changed, why it matters for the work you actually do, and one thing to try. Free while we tune it.