# Models & Auto mode

> Pick a model per thread, let Auto route per task, and control what your sub-agents run on.

Model choice isn't a global preference here. It's a per-thread decision you can change between turns, plus a separate decision about what the [sub-agents](https://darting.dev/docs/sub-agents/) inside that thread run on.

## The model picker

Every thread has a **model picker** in the composer. It sets which model the **lead agent** runs on, and you can change it at any point — the next turn simply uses the new one, with the same conversation and the same sandbox behind it. So a thread can start on a fast model while you scope the work, move to a stronger one for the hard middle, and drop back down for cleanup.

The selectable list is a registry maintained by the platform rather than something you configure. New models appear when they're supported; retired ones rotate out, so you're never pinned to a model that no longer exists.

## Auto mode

**Auto** hands the choice to the router instead. It picks per task rather than per thread, and it **escalates**: a task that proves harder than it looked moves up to a stronger tier mid-flight.

The point is that most turns don't need the frontier model. Renaming a symbol, reading a file, answering "where does this live?" — those are cheap. Untangling a race condition isn't. Auto keeps the cheap turns cheap without making you predict, turn by turn, which kind you're about to send.

## Sub-agents have their own setting

The lead's model doesn't have to be the swarm's model. Sub-agents get their own per-thread setting:

| Setting | What it does |
| ------- | ------------ |
| **Inherit** | Sub-agents run on the same model as the lead. |
| **Auto** | Each spawn is routed by its task, independently of the lead. |
| **Pinned** | Every sub-agent runs on the model you choose. |

This is worth tuning. A [coder](https://darting.dev/docs/agent-roles/) typing a slice the lead already planned, or an explorer reading files, can often run a tier below the lead that's holding the whole plan in context — that's the [delegation](https://darting.dev/docs/delegation-and-review/) pattern paying off twice. Some specialized fixer roles keep their own pinned defaults regardless, because the job is narrow and the right model for it is already known.

## Model choice is a cost lever

Pricing differs per model, and usage is metered per person — see [usage & limits](https://darting.dev/docs/usage-and-limits/) for where that shows up. Between Auto, a cheaper tier for sub-agents, and [delegation keeping the lead's context small](https://darting.dev/docs/compaction-and-context/), you have three independent dials on what a thread costs.