Hi @leoing ,
Out of interest, why do you say that?
Do you mean in terms of the context-window size or something else?
And why would there be different considerations for model selection in Composer (Ctrl + I) as opposed to model selection in Ctrl + L?
There is some uncertainty around context-window sizes in Cursor which I captured in the post below.
But it seems, when used in Cursor, gpt-4o has a 20k window, whereas claude-3.5-sonnet has a 10k window?