Unclear Whether the effort and fast-mode choices can actually be set yet is not known; only the model choice was traced to /model.
What
The agent view (also called the fleet view) shows and starts several sessions. It gains settings that apply only to new sessions started from that window and are not saved.
/model <name>now goes through a shared setter. Its hint says, for example, 'Model set to ... for new sessions from this window (not saved)'. Before, the hint said the model was session-scoped and not persisted.- A bare
/model, or one with an unknown name, now opens a setting picker instead of a usage hint. It offers model suggestions, the effort levels, on and off for fast mode, and a 'Reset to configured default' option. - The effort hint mentions
CLAUDE_CODE_EFFORT_LEVELwhen that variable overrides the choice. - The fast mode hint warns that fast mode draws from usage credits at a higher rate and that cloud sessions don't get it.
- The view is now created with an
activeTabargument, and the new-session settings are tracked.
Only the /model path was traced. Nothing was found that sets effort or fast mode through the setter, so those two may not be reachable yet.
Why
From the agent view you can pick the model for sessions you start next without changing your saved settings. Effort and fast mode controls may follow.
`<gcp_base_url>/projects/<project>/locations/<region>/publishers/anthropic/models/<model>:rawPredict`,see the edit
On Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6, thinking is off until you set `thinking: {type: "adaptive"}`, which lets Claude determine when and how deeply to think based on the request. The same request, wit…see the edit
| `model` (java, php; csharp, go: `Model`) | Required. The Claude [model](https://platform.claude.com/docs/en/models/overview) that powers the agent. Accepts a model ID string or an object, for example `{"id": "claude-opus-5-5"}`. Claude 4…see the edit
| `400` errors naming `thinking` or `adaptive`, such as `Input tag 'adaptive' found` | The upstream model build doesn't accept adaptive reasoning, which Claude Code requests for Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 5.5, Claude …see the edit
| [Adaptive reasoning](/docs/en/model-config#adjust-effort-level) | No beta header. Claude Code sends `thinking: {"type": "adaptive"}` for Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 5.5, Claude Fable 5, and later models, and treats m…see the edit
* Users choose among a tier's allowed models in the Claude Desktop model picker, described in [Models in Claude Desktop](/docs/government/desktop/models). Some models also offer a 1M context window, which Anthropic sets per model and which…see the edit
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.
| `set_model(model)` | Change the model for the current session. Pass `None` to reset to [Claude Code's default model](/docs/en/model-config). A session in `auto` mode [changes to `default` mode](/docs/en/agent-sdk/permissions#auto-mode-au…agent-sdk/python see the edit
| `GET` | `/v1/models` | `ListModels` | Data |api/claude-platform-on-aws-iam-actions see the edit
Whether the effort and fast-mode choices can actually be set yet is not known; only the model choice was traced to /model.
/model on Use Claude for M365 with third-party platforms
Added /effort and /fast in agent view to set what new sessions start with; a bare /model, /effort or /fast there now opens a picker