Claude Code v2.1.68: Opus 4.6 defaults to medium effort, reintroduces ultrathink keyword
Claude Code v2.1.68 release notes
Anthropics has released Claude Code v2.1.68 with changes to effort settings and model availability. This update primarily affects how the Opus 4.6 model handles different types of coding tasks.
Key changes in this release
- Opus 4.6 default effort changed: For Max and Team subscribers, Opus 4.6 now defaults to medium effort instead of the previous setting. According to the release notes, "Medium effort works well for most tasks — it's the sweet spot between speed and thoroughness."
- Effort control: Users can change the effort setting anytime using the
/modelcommand. - UltraThink keyword reintroduced: The "ultrathink" keyword has been re-added to enable high effort for the next turn. This allows users to temporarily boost the model's processing for complex tasks without permanently changing settings.
- Model deprecation: Opus 4 and Opus 4.1 have been removed from Claude Code on the first-party API. Users who had these models pinned are automatically moved to Opus 4.6.
The release was published on March 4th by ashwin-ant and includes commit 0b3f7cb. These changes are specific to Claude Code, Anthropics' coding-focused implementation of their Claude models.
📖 Read the full source: GitHub Claude-Code
👀 See Also
Lovable offers $100 free Claude API credits for International Women's Day
Lovable is giving away $100 in Anthropic Claude API credits, $250 in Stripe fee credits, and 24-hour free access to their platform through March 8. Users need to claim the offer before 12:59 AM ET on March 9.
Longitudinal study finds AI productivity gains at 10%, not 10x
A longitudinal study tracking 40 companies from November 2024 through February 2026 found AI usage increased by 65% on average, but pull request throughput only increased by 9.97%. The data suggests coding was never the primary bottleneck in software development.
Merlin Research releases Qwen3.5-4B-Safety-Thinking model for structured reasoning
Merlin Research has released Qwen3.5-4B-Safety-Thinking, a 4 billion parameter safety-aligned reasoning model built on Qwen3.5. The model is designed for structured 'thinking' and safety in real-world scenarios including agent systems.
Claude Code v2.1.157: Auto-Load Plugins from .claude/skills, Improved Agents & Worktrees
Claude Code v2.1.157 automatically loads plugins from .claude/skills, adds claude plugin init scaffolding, honors agent setting in settings.json, and fixes numerous bugs across agents, worktrees, and terminal integration.