News for hackers. Stuff that matters.
Re:Try Deep Think in the Gemini App by danenania on Friday August 01, 2025 @03:40PM (#44761451)
Input tokens usually dominate output tokens by a lot more than 2x though. It’s often 10x or more input. It can even easily be 100x or more. Again in realistic workflows.

Caching does help the situation, but you always at least pay the initial cache write. And prompts need to be structured carefully to be cacheable. It’s not a free lunch.

There are no comments on this comment yet.