Unclear It is not stated which models other than Fable use this consent prompt.
What
Some models can be used only after you agree to spend usage credits on them, through a one-time consent prompt. That handling used to be written for the Fable model alone. It now works for any model, and the related messages name whichever model is involved.
- Consent is now recorded separately for each model in
usageCreditsOnlyModelConsent. Fable still keeps its existingfableOverageConsentV2record. Before, consent was read only fromfableOverageConsentV2. - The
/modelcommand suggested in these prompts now points at the model that needs consent. - The
--advisorerror and the message shown outside an interactive session fill in the model name and a suggested command, for example "Run ... to review and enable." and "pick ... from /model in an interactive session to set it up". Before, they always said "Run /model fable" and "pick Fable from /model". - The limit message "You've reached your Fable limit." now appears only when the model is actually Fable. The high-demand banner shows "Fable" when the model is not a known one.
Why
More models can now sit behind a usage-credits consent prompt. The messages and suggested commands now match the model you are using, so you are not told to enable or switch to Fable when Fable has nothing to do with it.
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.
If you need a larger window rather than a smaller conversation, Fable models, Sonnet 5 and later, Haiku 5.5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [Extended context](/docs/en/model-config#extended…context-window see the edit
Fable 5.1 requires Claude Code v2.1.257 or later. Fable models require [Fable access](/docs/en/model-config#work-with-fable). Sonnet 5.5 as the advisor for an Opus 4.7 or Opus 4.8 main model requires Claude Code v2.1.287 or later. Haiku 5.…advisor see the edit
It is not stated which models other than Fable use this consent prompt.
Anthropic's documentation has since written up /model, on Escalate hard decisions with the advisor tool.