OpenAI adds new GPT-5 models, restores o3, o4-mini and it's a mess all over again

One of the few things many disliked about ChatGPT was the confusing number of models. OpenAI claimed GPT-5 would fix this, but it seems to have made it worse.

A new update is rolling out to ChatGPT. It doesn’t upgrade GPT-5, but instead adds more options that some of you would love.

Previously, GPT-5 had two variants – GPT (auto-rotates between reasoning and non-reasoning) and GPT-Thinking (reasoning).

GPT-5
GPT-5 model selector
Source: BleepingComputer

Today’s update populates the ChatGPT 5 model selection menu with several options.

Under GPT-5, you can choose Auto (decides how long to think), Fast (instant answers), Thinking mini (thinks quickly), Thinking (takes longer for better answers), and Pro (research-grade intelligence, requires upgrade).

You can choose the model that best suits your requirements, but if you select GPT-5, which is the default state, OpenAI will automatically pick the best model depending on the query.

There’s also a Legacy models section, which includes GPT-4o, GPT-4.1, o3, and o4-mini.

GPT-5 Legacy

If you don’t see the Legacy section, open your profile tab, then select Settings and turn on Legacy models. This works only on ChatGPT Plus and Pro accounts.