Copyright © 2022-2026 basebox GmbH, all rights reserved.
Licensed to be used in conjunction with basebox, only.

// ai chat

Thinking Modes

Brief description

With models that support it, you can decide how thoroughly the assistant should think before it answers. You can follow its reasoning in a separate area and collapse it at any time.

What are thinking modes used for

For complex tasks (analyses, multi-step reasoning, code), more thinking usually produces better answers, but it takes longer. For simple questions, a lower thinking effort is enough and you get an answer more quickly.

Where to find the setting

You choose the thinking mode directly in the chat. Administrators set the default per app and installation-wide.

Step by step

1. Open a chat with a model that supports thinking modes.
2. Choose the desired thinking effort.
3. Ask your question.
4. Open the thinking area if you want to see the reasoning – or collapse it when you only need the answer.

Notes

Note

• Not every model supports thinking modes.
• Thinking modes are also available via the OpenAI-compatible API (see OpenAI-compatible API).

Frequently asked questions

Does more thinking cost more time? Yes, more thorough thinking increases the response time.

Can I hide the reasoning? Yes, the thinking area can be collapsed at any time.