Model and effort

Every session runs on one model at one reasoning effort. Together they set how thorough or how fast the session is.

Model

/model lists the models your organization's model provider offers, most powerful first: Fable, Astra (GPT 6), Opus, Sol (GPT 6.1), Grok 4.7, Terra (GPT 5.6), and Sonnet.

Fable is the recommended choice for deal work: it's the most thorough, and it often takes longer to respond. Sonnet and Terra are the fastest; use one when you want quick answers more than depth. Opus is the middle option: use it when Fable's pauses are too long for the task but you want more depth than Sonnet.

When an admin has enabled a faster speed for a model, it appears as its own row, so one pick sets the model and its speed. The choice holds for the rest of the current session. New sessions open on Opus at standard speed until an admin picks a different Model in Workspace settings.

Effort

/effort sets how much reasoning goes into a response. Choose Low or Medium for light work, High for a balance of depth and speed, or Extra high and Max for deeper analysis. Ultra is available on Fable, Opus, and Sonnet only; Grok stops at Extra high.

New sessions use High on Fable, Opus, Astra, and Grok, or Extra high on Sonnet, Sol, and Terra. An admin can change Reasoning effort under Workspace settings > Session defaults. Switching models keeps your effort if the new model offers it; otherwise it changes to Extra high.

To show or hide the terminal's thinking display, use /show-thinking.

A second opinion

The terminal can consult a senior reviewer model about its own work. While it does, the conversation reads "Asking the VP", and the status line names the reviewer.

/ask-vp turns those consultations off or back on for the current session. Run it on its own to pick between the reviewer and "No VP", or type /ask-vp off and /ask-vp on to switch it directly. An admin sets whether the organization has Ask the VP at all, and which model reviews, in Workspace settings.

Learn more

• Workspace settings: the model, effort, and reviewer new sessions open on, set by an admin.
• While the terminal works: what long pauses look like and when to worry.
• Model provider: the choice, for the whole organization, of which service processes model requests, set by an admin.