Models and cost

Choosing a model

A managed blend picks the right model per job, or pin one yourself.

CtrlM opens the picker. /model prints the current one; /models opens the picker from the keyboard.

The default does the routing

Premium is a blend, not a single model. Different parts of a job go to different frontier models — the one that plans well plans, the one that edits precisely edits. You don't manage it.

Most people never change this.

Pinning one

Code
/model deep        favour capability
/model fast        favour latency
/model premium     back to the blend

Pin a specific model when you have a reason:

Code
/model anthropic/claude-opus-5
/model groq/llama-4-maverick

The pin lasts for the session. The status line always shows what's active.

When pinning is worth it

  • A long mechanical run — a cheaper model, since the work is repetitive.
  • One genuinely hard problem — the most capable model for a few turns.
  • Reproducing something — same model, same conditions.
  • You have your own key — see Using your own API keys.

Cost follows the model

Managed calls bill ContextStream credits at the live rate for whichever model ran. The status line shows the cost of the turn as it happens; /usage breaks the session down by model.

Pinning a cheap model makes turns cheaper. Pinning an expensive one makes them dearer. There's no flat rate hiding the difference.

If it doesn't work

The picker shows models I can't use. Managed tiers need credits; your own providers need a key configured. The picker says which is which.

It switched back to premium. Pins are per session. /model at the start of a session, or set a default in settings.json.

A pinned model is failing. Provider outage or a rate limit. Switch with CtrlM; the conversation carries across.

Next