Use different cloud models per role
1 min · 3 steps
Send reasoning to one model, completion to another, vision to a third. Per-role overrides let you mix and match.
Avery's planner splits requests into roles (`coding`, `reasoning`, `embedding`). Without overrides, every role uses the default cloud provider + model. Overrides let you route — for example — coding to Claude Sonnet but reasoning to o3.
Steps
- Make sure you're in cloud-only mode.
Per-role overrides only apply when routing mode is `cloud-only`. Local-first routing uses the local SLM's role assignments instead.
- Expand 'Per-role cloud overrides'.
It's a collapsed card just below the default-cloud-provider picker on Settings → AI → Model.
- Pick a provider + model per role.
Each row gives you a provider dropdown (limited to providers you've connected) and a model picker. 'Use default cloud provider' clears the override.
Live recipes need the desktop
This article is a static preview. The in-app Help sidecar inside Avery NXR can fire each step against your live project — install the desktop to use it interactively.