Openai is working on a new feature called the thinking attempt picker for chat.
With thinking picker, you can choose how chat can think. When a model thinks hard, it is not necessarily a great response.
You don’t want models to think hard when you are not sure what to do tomorrow.
However, you want the model to find it difficult when you are working on a complex subject, such as Econometrics, Bond Valuation, Healthcare and so on.
As Moldy On X, Openai is testing the attempt picker, so you can choose the intensity of the thinking model.
Right now, there are four levels. The lowest level is called light and has an internal feature of 5, while the standard sits on 18, the extended is 48, and the Max is 200.
The number is an internal “juice” budget. More juice means that the model takes more steps and usually gives a deep answer, but it reacts slowly.
Max Thinking (200) is a gate, which means that it is available only to people with $ 200 membership (Pro Plan).
While the details are not clear, Bleepingcomputer understands that Openai wants to give more control to users.
If you really understand how no model works for the type of questions.
For example, you can choose light for quick questions, standard for everyday use, extend to moderate complexity, and maximum when you need the most careful analysis.
The passwords broke in 46% of the atmosphere, almost doubled by 25% last year.
Picus Blue Report 2025 Now get a wider look at more conclusions on prevention, detection and data exfIs.
