The model picker
One list, every engine. Pick a model by hand, or let Companion pick for you.
At the top of every conversation sits the model picker. It shows a single catalog built from every engine you’ve paired — local clusters, Telemak Macs, cloud providers — each with its real capabilities (tools, vision, thinking) read from the capability contract.
Three levels of control
Section titled “Three levels of control”| Mode | What you choose | For |
|---|---|---|
| Easy | nothing — Companion auto-routes | ”just answer me well” |
| Advanced | one model, by hand | you know which model you want |
| Expert | model + sampling, thinking, effort | tuning a specific behaviour |
Easy — auto-routing
Section titled “Easy — auto-routing”In Easy mode Companion picks the model for you with a fast semantic router: it embeds your message and routes it to one of a few buckets (e.g. quick / code / deep). This is Companion’s own chat router — cheap (~milliseconds) and tuned for the chat use case.
Auto-routing in chat is separate from CoeOS. CoeOS is the engine-side, benchmark-grounded router for agents; the chat picker’s router is for you, in the window. Both can be in play, at different layers.
Advanced — pick a model
Section titled “Advanced — pick a model”Open the picker, choose a model. It sticks for the conversation until you change it. The list shows the engine each model belongs to and flags what it supports, so you won’t, say, attach an image to a text-only model.
Expert — tune it
Section titled “Expert — tune it”Expert mode exposes the dials: temperature and the sampling parameters, the
Thinking toggle (enable_thinking), and reasoning effort
(minimal → high). Useful when you want a model to stop over-thinking a simple
ask, or to reason harder on a deep one.
Switching mid-conversation
Section titled “Switching mid-conversation”You can change the model at any turn — the history stays, the next answer comes from the new model. Because the KV prefix cache is keyed per conversation, switching to a local model re-prefills (a one-time cost); switching to a cloud model just changes who bills the tokens.
Read next
Section titled “Read next”- The chat window — where the picker lives.
- Engine pairing — how engines get into the catalog.
- CoeOS — the engine-side per-skill router, for agents.