Claude Sonnet 5.5 replaces Sonnet 5

The model

• Claude Sonnet 5.5 (claude-sonnet-5-5) replaces Sonnet 5 in TeamDay's model picker, right below Opus 5.5. Anthropic released it on September 28.
• 1M token context window and up to 128k output tokens.
• Same price as Sonnet 5: $2 / $10 per million tokens (input / output), with cache hits at $0.20. Same tokenizer, so token counts don't change.
• Anthropic recalibrated its reasoning-effort levels, so TeamDay starts it at medium, Anthropic's suggested level for agent work. You can still pick anything from low to max.

What happens to Sonnet 5

• Existing agents and chats set to Sonnet 5 move to Sonnet 5.5 automatically. You don't need to do anything, and the price stays the same.

The Claude lineup in TeamDay

• Opus 5.5: the default for everyday and complex work.
• Sonnet 5.5: half Opus 5.5's price, for routine work at volume.
• Fable 5.1: the most capable option, for the hardest and longest-running tasks.
• Haiku 4.5: fastest for quick answers.