Claude Code Makes Opus the Default Model on Pro and Team Standard Plans
Claude CodeClaude Code 2.1.280 switched the default model on Pro and Team Standard plans from Sonnet to Opus, matching Max, Team Premium, and Enterprise, which already defaulted to Opus. The change landed the same day as Claude Opus 5.5, so Pro and Team Standard users who change nothing now run the cheaper, faster Opus 5.5 by default instead of Sonnet. Anthropic also changed how saved per-model effort levels behave: a level chosen before /effort became per-model no longer carries over to newly released models such as Opus 5.5, which start at their default effort until a user picks one.
Key Takeaways
- Sonnet is no longer the Pro-tier default: Pro and Team Standard accounts now start every session on Opus instead of Sonnet, closing the gap with Max, Team Premium, and Enterprise plans.
- The switch is timed to Opus 5.5's price cut: Anthropic flipped the default the same day Opus 5.5 launched with 20 to 60 percent lower per-token pricing, softening the usage-limit hit of defaulting to a bigger model.
- Sonnet is still one click away: users who prefer the lighter usage footprint can still pick Sonnet manually through
/model; nothing about model availability was removed. - Saved effort levels no longer leak into new models: an effort level chosen before
/effortwas per-model will not silently apply to Opus 5.5 or future models, which now start at their own defaults. - Older models lose their effort override too: Opus 4.7, Opus 4.8, and Fable 5 no longer hold onto their launch-default effort over an explicitly configured
/effortlevel. - A quiet but consequential
Changedbullet: this is a default-behavior flip, not an opt-in feature, so Pro and Team Standard users will notice higher-quality (and higher-cost) responses without having changed any setting themselves.
Sources & Mentions
5 external resources covering this update
Anthropic releases Opus 5.5 with lower prices and Fable-level performance
TechCrunch
Anthropic Launches Claude Opus 5.5 With Fable-Level Performance at a Lower Price
MacRumors
Claude Opus 5.5 Benchmarks Explained
Vellum Blog
Claude Opus 5.5: An evaluation review and metrics benchmarks
Security Boulevard
Claude Code Models (September 2026): Best Model for Claude Code
Morph LLM Blog
Opus Becomes the Default Across Every Plan
Prior to September 22, 2026, Sonnet was the default model on Claude Code's Pro and Team Standard plans, while Max, Team Premium, and Enterprise already defaulted to Opus; Pro-tier users could switch to Opus manually, but it was not the out-of-the-box experience. Release 2.1.280 closed that gap: every plan tier now starts a new session on Opus by default.
What Changes for Pro and Team Standard Users
The practical effect is that Pro and Team Standard accounts that take no action are now running Claude Opus 5.5, Anthropic's newest and (per the same release) considerably cheaper Opus model, rather than Sonnet. Because Opus 5.5's per-token pricing was cut at the same time this default flipped, the jump to a bigger default model arrives with a smaller usage-limit penalty than switching to Opus would have carried under the older Opus 5 pricing. Anyone who prefers Sonnet's lighter usage footprint can still select it manually through /model.
A Related Change to Effort Levels
Alongside the default-model switch, Anthropic changed how a saved effort level behaves when a new model ships. Previously, an effort level set before /effort became a per-model setting could silently apply to models released later. Going forward, an effort level saved that way will not apply to newly released models such as Opus 5.5; those models start at their own default effort until a level is explicitly chosen for them. A related change removed the special case that let Opus 4.7, Opus 4.8, and Fable 5 keep their launch-default effort over an explicitly configured /effort level, whether set via -p, the Agent SDK, project or managed settings, or a per-model level.