Follow Discord
Sweep 10 Nov 2026 · 02:18Z Build v2.1.322 539 read Stable v2.1.311 Latest v2.1.322 Next v2.1.322 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.283 ·

Opus 5.5 can fall back to Opus 5 for one more refusal type

When claude-opus-5-5 refuses a request in the frontier_llm category, Claude Code can now fall back to claude-opus-5

You'll notice Improvements
JSON All of v2.1.283
You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
4Signal: worth watching, 1 to 5
ModelsArea: what it touches
ImprovementsKind: in v2.1.283,
What probably matters to youSection of the release

Unclear Whether the refusal fallback feature itself is switched on for everyone is not settled.

What

Claude Code keeps a list of which model to fall back to when the session's model refuses a request in a given category. For sessions on claude-opus-5-5, that list now includes the frontier_llm category, which falls back to claude-opus-5. Before, only the bio and cyber categories had fallbacks. The default list gains the same entry.

Why

If you use Opus 5.5 and hit this kind of refusal, Claude Code may now retry on Opus 5 instead of stopping at the refusal.

Read from
Names in the bundleclaude-opus-5-5claude-opus-5
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 prompting-claude-opus-5-5 touched a line naming claude-opus-5-5 after this was published. * **Reasoning extraction:** Requests that push the model to reproduce its internal reasoning in the response text may be declined with the `reasoning_extraction` category. If your prompts ask the model to write out its reasoning in the res… build-with-claude/prompt-engineering/prompting-claude-opus-5-5 see the edit
Added since A small documentation edit on prompting-claude-opus-5-5 touched a line naming claude-opus-5 after this was published. * **Reasoning extraction:** Requests that push the model to reproduce its internal reasoning in the response text may be declined with the `reasoning_extraction` category. If your prompts ask the model to write out its reasoning in the res… build-with-claude/prompt-engineering/prompting-claude-opus-5-5 see the edit
Confirmed since Anthropic's documentation has since written up claude-opus-5-5, on advisor-tool. | Claude Haiku 4.5 (claude-haiku-4-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opu… agents-and-tools/tool-use/advisor-tool see the edit
Confirmed since Anthropic's documentation has since written up claude-opus-5, on advisor-tool. | Claude Haiku 4.5 (claude-haiku-4-5) | Claude Mythos 5.1 (claude-mythos-5-1) Claude Fable 5.1 (claude-fable-5-1) Claude Mythos 5 (claude-mythos-5) Claude Fable 5 (claude-fable-5) Claude Opus 5.5 (claude-opus-5-5) Claude Opus 5 (claude-opu… agents-and-tools/tool-use/advisor-tool 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 doubtWhether the refusal fallback feature itself is switched on for everyone is not settled.
Anthropic's documentation agreesAnthropic's documentation has since written up claude-opus-5, on advisor-tool.

See this entry in the whole of v2.1.283 →

Feedback