ChatGPT now gives you greater control over GPT-5 Thinking model

by CybrGPT
0 comment

OpenAI is finally rolling out a toggle that allows you to decide how hard the GPT-5-thinking model can think.

This feature is rolling out to Plus and Pro subscribers.

OpenAI has been testing the toggle for several weeks now. Previously, OpenAI planned to ship a slider, but it has now opted for a simple toggle for controlling thinking model.

GPT 5 Thinkingq
GPT-5 Thinking Model control
Source: BleepingComputer

As you can see in the above screenshot, toggle allows you to select GPT-5 Thinking with different reasoning effort levels. The effort levels are internally called “juice” values.

For example, GPT-5-Thinking is set to a level of 18 when you’re using Standard. This is the default balancing speed and intelligence.

Finally, you have Extended, which has a level of 64.

In the case of Pro, you can also choose Light, which has a juice level of 5, and is very instant. But if you’re looking for deeper thinking, you can use Heavy, which has a level of 200, the maximum you can get out of GPT-5-Thinking model.

These models are available to Plus and Business users, while Pro users get Light and Heavy as well.

Picus Blue Report 2025

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.

Source link

You may also like

Leave a Comment

Stay informed with the latest in cybersecurity news. Explore updates on malware, ransomware, data breaches, and online threats. Your trusted source for digital safety and cyber defense insights.

BuyBitcoinFiveMinute

Subscribe my Newsletter for new blog posts, tips & new photos. Let’s stay updated!

© 2025 cybrgpt.com – All rights reserved.