Claude Sonnet 5.5 adds between_tools thinking capability flag
Models API now documents a capabilities.thinking.types.between_tools flag indicating whether a model accepts thinking: {type: "between_tools"}. Sonnet 5.5 reports supported=true while disabled=false, so callers must check the flag rather than assume behavior.
Impact Assessment
Alternative models
Directional candidates based on stored listed rates and editorial scenario tags; validate quality and current terms before switching
Significant cost savings • Similar use cases
Significant cost savings • Similar use cases
Good value alternative • Similar use cases
Slightly cheaper option • Similar use cases
Significant cost savings • Similar use cases
Sources
Each model's capabilities object also includes thinking.types.between_tools , which reports whether the model accepts thinking: {type: "between_tools"} , the setting that turns off up-fro...
Comments
Does this change your best option?
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.