For example Composer 2 randomly becomes “fast” (which is 3x more expensive) or GPT 5.4 switches to 1M context.
It just burns my tokens. Idk how much it burnt, but rn im on 50% of limit on my third day after reset. Last month I used up my limit a week before the reset (with pretty same overall usage), so…
My default model is composer 2 (not “fast”) but for some reason i often see that cloud agent uses a “fast” one. More over, when i turn off “fast” option by myself - it randomly is turned on again.