Hacker News Reader

I wonder what's the difference between this and GPT 5.5 thinking with zero thinking effort? Interesting product decision to have different models.

View on HN

Good question. I find that GPT-5.5 thinking is very good at not thinking for simple questions, so much so that I've never had the need to use the instant model even for quick Q&A.

I'm assuming the instant model, then, is an entirely different smaller model mainly serving the free tier of ChatGPT.

It is an entirely free model, but it is also the model that most users (even paid) interact with until the router pushes the thinking.

Good point. I feel like this does a disservice to ChatGPT -- IIRC even the free tier of Claude points you to Sonnet 4.6 by default, which is magnitudes better than 5.3-instant which has been the default in ChatGPT.

Hence most users will immediately think Claude is smarter, even if their best models are on par.

then again I think the free sonnet 4.6 only allows ~5 requests a day but GPT allows more than 50

Correct. I have the $20/month plan and I just checked, the default is 5.3-instant. I can manually switch it to Thinking is 5.5. I also have it set to auto-switch.

Reply on news.ycombinator.com