Model Fatiguehttps://modelfatigue.news/Another model. Measured. Which AI model to use for what, at what effort, and what it costs.Sonnet 5.5 is cheaper than Sonnet 5, until you turn it up to maxhttps://modelfatigue.news/v/sonnet-5-5/https://modelfatigue.news/v/sonnet-5-5/Tue, 29 Sep 2026 12:00:00 +0000Anthropic says Sonnet 5.5 needs far fewer tokens than Sonnet 5 for the same work. Artificial Analysis says it uses more output tokens per task than any model it has measured. Both are right, at different effort settings.