How to enable reasoning in gemini-2.0-flash-thinking-exp-01-21 with ChatGoogleGenerativeAI?

[DecX-x]

I'm using ChatGoogleGenerativeAI in LangchainJS with gemini-2.0-flash-thinking-exp-01-21, but I noticed that there is no thinking or reasoning output.

Is there any way to enable a "thinking mode" for this model in ChatGoogleGenerativeAI? Are there specific configuration? Any insights would be really helpful!

const model = new ChatGoogleGenerativeAI({
  model: "gemini-2.0-flash-thinking-exp-01-21",
  apiKey: gemini_api,
  temperature: 0.7,
  streaming: true, 
  
});

[andantonyan]

Hi @DecX-x

From their documentation:

Models with thinking capabilities are available in Google AI Studio and through the Gemini API. Note that the thinking process is visible within Google AI Studio but is not provided as part of the API output.

Google AI Studio Documentation