@sama Then give us the ability to speak with the older models again outside of the api. You could hide it in the settings or behind subscriptions if you're worried about confusing new users. But I miss chatting with some of those older models.
@KyleHessling1 Congrats on the release. I think this is really cool. I have to ask, is there a way to turn off the thinking for lower latency tasks? I tried a few tricks that worked with qwen3.5 but didn't have much luck.