What
/model switches the AI model Claude Code uses. In a cloud session, the work runs on a remote machine (a worker) instead of your own computer. The model switch can now ask that remote request to wait until the worker has started, and then carry out a follow-up step once the switch has gone through. Before, the request was sent with no such option.
Why
Switching models in a cloud session that is still starting up should work more reliably.
Names in the bundle/model
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.
Confirmed since
Anthropic's documentation has since written up /model, on pricing.
| Claude Opus 4.1 ([retired, except on Claude Models on Google Cloud (Google managed) and Bedrock](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | $15 / MTok | $18.75 / MTok | $30 / MTok | $1.50 / MTok | $75 / MTok |about-claude/pricing see the edit
Added since
A small documentation edit on model-ids-and-versions touched a line naming /model after this was published.
For the full list of current model IDs and their equivalents on Claude Models on Google Cloud (Google managed) and Amazon Bedrock, see [Models overview](https://platform.claude.com/docs/en/models/overview).about-claude/models/model-ids-and-versions see the edit
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agrees
A small documentation edit on model-ids-and-versions touched a line naming /model after this was published.