Comment by varenc
4 hours ago
Interesting that they're releasing separate gpt-5.1-instant and gpt-5.1-thinking models. The previous gpt-5 release made of point of simplifying things by letting the model choose if it was going to use thinking tokens or not. Seems like they reversed course on that?
> For the first time, GPT‑5.1 Instant can use adaptive reasoning to decide when to think before responding to more challenging questions
It seems to still do that. I don't know why they write "for the first time" here.
For GPT-5 you always had to select the thinking mode when interacting through API. When you interact through ChatGPT, gpt-5 would dynamically decide how long to think.