Tabbit
Anthropic released Claude Opus 5.5 on September 22, 2026, with API model ID claude-opus-5-5. Its documentation lists a 1M-token context window, up to 128K output tokens, and medium as the default effort. Availability in Tabbit depends on your account's live model picker.
Use in Tabbit Claude Opus 5.5
Claude Opus 5.5 · Model overview
A compact view of reviewed task guides, public evaluations, and evidence boundaries. Client access still depends on your current account.
Model access and permissions must be checked in the current Tabbit account.
Extract structured data, build a visual prototype, or start a coding task.
This official guide provides ready-to-use prompt snippets and API adjustments for Opus 5.5’s thinking budget, long-running task continuation, progress updates, cross-app retrieval, chat latency, pasted-text injection, and frontend design.
Claude Opus 5.5 always has adaptive thinking enabled. When migrating, use effort to control reasoning depth and check compatibility with forced tool calls, thinking-block handoff, and computer-use tools.
This personal CLAUDE.md configuration sets out project scope, concise communication, dependency-documentation lookup, checks, and delegation boundaries as work preferences Claude Code can load; the author recommends reviewing it against the project before merg.
AWS documentation lists the model IDs, regional routing options, and API support for Claude Opus 5.5 on Bedrock Runtime and Bedrock Mantle. It also provides an example request to the Runtime Messages API using the Anthropic Python SDK.
Public results use different versions, tiers, and harnesses; unknown values stay unknown.
Anthropic's published results show Claude Opus 5.5 performing strongly on selected agentic coding, knowledge-work, and computer-use benchmarks, and claim that its typical workload costs 40% less than Opus 5; these figures come from vendor-published material, a.
METR's preliminary evaluation finds that Claude Opus 5.5 makes incremental gains over Fable 5.1 across several AI R&D-related tasks. It may modestly increase researcher productivity, but there is no evidence that it can fully automate AI R&D.
On SonarSource's Java coding tasks, Opus 5.5 High's measurable task pass rate was less than one percentage point below Opus 5 Thinking's. Opus 5.5 generated less code and fewer issues overall, but had higher bug and concurrency issue densities per line of code.
Anthropic
Explore Claude Opus 5.5 specifications, prompting guidance, and evaluation evidence, then check availability in your account's live model picker.