Fable - anything requiring "thinking" or judgement--usually design and architecture

Opus - smart execution (most coding, knowledge work)

Sonnet - dumb execution (basic coding, generic text/organization/information tasks)

Haiku - really only reason is lack of auto mode becomes tedious. I only use it indirectly with sub agent delegation for text analysis (summarize web page, document). However, it's quite fast and capable

Those distinctions make sense. I guess I'm more interested as to "when" you make that decision. What triggers you to spend the cognitive energy on deciding which model?

[dead]