Gemini 2.0 Flash Thinking is an experimental model that's trained to generate the "thinking process" the model goes through as part of its response. As a result, Gemini 2.0 Flash Thinking is capable of stronger reasoning capabilities in its responses than the base Gemini 2.0 Flash model.
Use Flash Thinking
Flash Thinking models are available as an
experimental model in Vertex AI.
To use the latest Flash Thinking model,
select the
gemini-2.0-flash-thinking-exp-01-21 model in the Model drop-down menu.
Thoughts
The model's thinking process is returned as the first element of the
content.parts list that is created when the model generates the response. For
example, the following code prints out only the model's thinking process:
response = client.models.generate_content(
model='gemini-2.0-flash-thinking-exp-01-21',
contents='Solve 3*x^3-5*x=1',
config={'thinking_config': {'include_thoughts': True}}
)
Markdown(response.candidates[0].content.parts[0].text)
You can see more examples of how to use Flash Thinking in our Colab notebook.
Limitations
Flash Thinking is an experimental model and has the following limitations:
- 1M token input limit
- Text and image input only
- 64k token output limit
- Text only output
- No built-in tool usage like Search or code execution
What's next?
Try Flash Thinking for yourself with our Colab notebook, or open the Vertex AI console and try prompting the model for yourself.