Follow Discord
Sweep 25 Sep 2026 · 19:33Z Build v2.1.283 504 read Stable v2.1.274 Latest v2.1.283 Next v2.1.283 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.282 ·

/model no longer rejects a model as invalid when the only problem is that credits are required

When switching models with /model, a 'credits required' answer for a qualifying model no longer fails as an invalid model

Group of 2 Use it now Bug Fixes
JSON All of v2.1.282
Use it nowTier: how much it should matter to you
3Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
ModelsArea: what it touches
Bug FixesKind: in v2.1.282,
What probably matters to youSection of the release

What

/model switches the AI model Claude Code uses. Before a switch, Claude Code asks the server whether the model is valid. Until now, if the server answered with a 429 (a "too many requests" style refusal), the switch failed with a generic API error: … · model not changed message and was treated as an invalid model.

  • A 429 whose error_code is "credits_required" is now recognised and marked creditsRequired.
  • The interactive /model switch passes acceptCreditsRequired, telling the check it will accept that case.
  • If the model qualifies, validation now returns ok and keeps the refusal text as creditsRefusal. One member names the qualifying models as those whose name starts with claude-fable-, together with an account or billing check.
  • A model that does not qualify is still refused as before.

The findings describe the next step differently. One says the switch carries on into the normal model-confirmation step. Another says the refusal text is shown as a system message and the switch stops there without applying the model.

Why

If your plan needs credits for a certain model family, /model no longer calls that model invalid. You now see the actual reason, the credits message, instead of a generic error.

Read from
Names in the bundle/model
Since it was published

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.

Added since A small documentation edit on Customize Claude Tag touched a line naming /model after this was published. Channel members can also change the model from Slack. Asking Claude in a thread switches that thread, and asking it to make a model the channel default changes this setting for the channel, unless the scope's [Channel member edits](/docs/c… claude-tag/admins/customize see the edit
Confirmed since Anthropic's documentation has since written up /model, on Authentication for connectors. | `oauth_cimd` | OAuth 2.0 with [Client ID Metadata Document](https://modelcontextprotocol.io/specification/2025-11-25/basic/authorization#client-id-metadata-documents) | Supported by default | connectors/building/authentication see the edit
How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtIt is not clear which account condition applies or what the confirmation step shows.
Anthropic's documentation agreesAnthropic's documentation has since written up /model, on Authentication for connectors.
Anthropic's release notes agreeFixed earlier extended thinking being dropped when /model, /rename, /artifacts or another immediate slash command was used while Claude was…

See this entry in the whole of v2.1.282 →

Feedback