Unclear The prepared list may start empty, so it is unclear whether this changes the picker for anyone yet.
The /model command opens a picker for choosing a model and its effort level, which is how much work the model puts into each answer. The picker now accepts a prepared list of options instead of building its own. It also keeps your effort choice as you move between picks.
When you save a model as your default, the effort is saved only if it differs from the preset effort for that option.
This could change which models the picker offers, and stops a default from storing an effort that just repeats the preset.
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
On the Claude API and Claude Platform on AWS, the target list is published as `allowed_fallback_models` on each model's entry in the [Models API](https://platform.claude.com/docs/en/api/beta/models/list) when the `server-side-fallback-2026…build-with-claude/fallback-credit see the edit
| Has [`ANTHROPIC_DEFAULT_SONNET_MODEL`](/docs/en/model-config#environment-variables) set | Its value, or Sonnet 5 if its value is Claude Sonnet 5.5 or Claude Opus 5.5 |permission-modes see the edit
The prepared list may start empty, so it is unclear whether this changes the picker for anyone yet.
Anthropic's documentation has since written up /model, on Choose a permission mode.