Why is gpt5 272k context and not 400k?

[liquefy]

open ai api says 400k context https://platform.openai.com/docs/models/gpt-5 but cursor docs say 272k even in max mode, why is that?

[haris-musa (Haris)]

because it was found that it performs best till 272K context, beyond that the quality will drop

[nps-rf (Nikolai Pikalov)]

Hi, OpenAI’s GPT-5.2 has been released, why is it still only available in the context of 272k, despite the fact that OpenAI has improved the behavior of the model with more tokens?

---

[nps-rf (Nikolai Pikalov)]

I think a reasonable solution would be to simply transfer the remaining tokens to MAX mode, given that most of the OpenAI models (with rare exceptions) have no differences in abilities when using MAX mode.