Just started using OAI’s o1-preview model via the api.  Seems to be very capable. 

It fixed some code I was having trouble with in one shot. And built a working application with code examples in another one shot.  

The 32k token output is a game changer.

I’m curious to know if you’ve ever gotten it to print even close to 32k tokens in a response. I haven’t been able to, the most I’ve had it return was 18.5k (still extremely impressive, considering it was an entirely coherent response). It doesn’t seem to respond to requests for longer outputs.