OpenAI is working on a new feature called the Thinking effort picker for ChatGPT.
With the Thinking effort picker, you can choose how hard ChatGPT can think. When a model thinks harder, it doesn’t necessarily mean a great response.
You might not want the model to think harder when you’re not sure what to do tomorrow.
However, you may want the model to think harder when you’re working on a complex topic, such as econometrics, bond valuation, healthcare and so on.
As spotted on X, OpenAI is testing the effort picker, so you can select the intensity of the thinking model.
Right now, there are four levels. The lowest level is called light and has an internal attribute of 5, while standard sits at 18, extended is 48, and max is 200.
The number is an internal “juice” budget. More juice means the model takes more steps and usually gives a deeper answer, but it responds slower.
Max thinking (200) is gated, which means it’s only available to those with $200 subscription (Pro plan).
While details are unclear, BleepingComputer understands OpenAI wants to give users more control.
If you really understand how a model works for the type of questions.
For example, you can pick light for quick questions, standard for everyday use, extended for medium complexity, and max when you need the most careful analysis.
46% of environments had passwords cracked, nearly doubling from 25% last year.
Get the Picus Blue Report 2025 now for a comprehensive look at more findings on prevention, detection, and data exfiltration trends.
Get the Blue Report 2025