Google has announced the release of Gemini 2.0 Flash Thinking Mode which is an upgraded model over the base 2.0 Flash in terms of reasoning. “Gemini 2.0 Flash Thinking Mode is an experimental model that’s trained to generate the “thinking process” the model goes through as part of its response,” said Google.
Thinking Mode is available as an experimental model in Google AI Studio, and for direct use in the Gemini API. In other words, it is not available for general consumers in the Gemini app for now. Google says that the model’s thinking process is returned as a new section in the Thoughts panel in the response window. By default, the Thoughts panel is collapsed. You can expand the panel by clicking the Thoughts header. Unlike the returned response, the contents of the Thoughts panel are not editable in Google AI Studio.
Google further states that Gemini 2.0 Flash Thinking Mode is an experimental model and has the following limitations:
- 32k token input limit
- Text and image input only
- 8k token output limit
- Text only output
- No built-in tool usage like Search or code execution
Read More: Google Gemini 2.0 Announced: How Has it Improved Over Gemini 1.5?
The release of the Thinking mode reasoning model comes shortly after Google listed “2.0 Experimental Advanced” in the Gemini model picker on desktop and mobile web (excluding the app). Google describes this model as offering “significantly improved performance on complex tasks, including coding, math, reasoning, and instruction following.”
The model is designed to handle “complex tasks with greater ease,” and excels at addressing challenging coding problems, solving intricate math equations for academic or personal projects, and delivering comprehensive, multi-step instructions for crafting customized business plans.