Models, cost and fast mode

Three dials change what a session costs: which model, how much it reads, and how much of the conversation it carries. You have already met the second and third.

Choosing a model

/model switches mid-session and --model starts one. Sonnet handles most coding work. Opus is for reasoning that is genuinely hard, usually architecture or a bug nobody understands. Haiku is for volume: the subagent in lesson 20 searching a repository does not need your best model.

The useful habit is not picking the cheapest model. It is noticing that a lot of the work a session does is not the hard part, and routing that work away from the expensive one, which subagents make easy.

Seeing what it costs

/usage

It prints what has been used against your plan's limits.

The statusline from lesson 14 shows the same thing without asking, which is why that lesson exists this early. A number you see all day changes behaviour; a number you have to ask for does not.

For reference, the documentation puts the average across enterprise deployments at around thirteen dollars per developer per active day, with ninety per cent of users under thirty. If you are far above that, the cause is nearly always context rather than the model.

What actually reduces it

• Say where to look. A question that names the file skips the searching, from lesson 3.
• Deny reads of generated code. The last lesson.
• Delegate noisy work to a subagent on a cheap model. Lesson 20.
• Compact with a focus rather than letting it happen. Lesson 7.
• Start a new session for a new task. Carrying an unrelated conversation costs on every turn.

Fast mode

/fast is a different trade from all of the above: the same Opus model, configured to answer up to two and a half times faster, at a higher cost per token. It is not a smaller model and the quality is the same. It is in research preview.