News for hackers. Stuff that matters.
Re:Gemini 2.5 Flash by rfw300 on Thursday April 17, 2025 @03:50PM (#43721355)
o4-mini does look to be a better model, but this is actually a lot cheaper! It's ~7x cheaper for both input and output tokens.
Re:Gemini 2.5 Flash by ein0p on Thursday April 17, 2025 @04:29PM (#43721876)
These small models only make sense with "thinking" enabled. And once you enable that, much of the cost advantage vanishes, for output tokens.
Re:Gemini 2.5 Flash by overfeed on Thursday April 17, 2025 @04:41PM (#43722011)
> These small models only make sense with "thinking" enabled

This entirely depends on your use-cases.