zlacker

[parent] [thread] 2 comments
1. cbg0+(OP)[view] [source] 2025-05-06 19:08:13
o3 is $40/M output tokens and 2.5 Pro is $10-15/M output tokens so o3 being slightly ahead is not really worth 4 times more than gemini.
replies(2): >>jorl17+N2 >>i_have+8l
◧
2. jorl17+N2[view] [source] 2025-05-06 19:29:45
>>cbg0+(OP)
Also, o3 is insanely slow compared to Gemini 2.5 Pro
◧
3. i_have+8l[view] [source] 2025-05-06 21:34:51
>>cbg0+(OP)
Not sure why this is being downvoted, but it's absolutely true.

If you're using these models to generate code daily, the costs add up.

Sure, I'll give a really tough problem to o3 (and probably over ChatGPT, not the API), but on general code tasks, there really isn't meaningful enough difference to justify 4x the cost.

[go to top]