Google has introduced an updated version of its AI model for problem-solving, known as Gemini 2.0 Flash Thinking. This experimental version became available for testing in January 2025. The model has received several new features that enhance its understanding and usability.
We are rolling out a new Gemini 2.0 Flash Thinking update:
— Logan Kilpatrick (@OfficialLoganK) January 21, 2025
– Exp-01-21 variant in AI Studio and API for free
– 1 million token context window
– Native code execution support
– Longer output token generation
– Less frequent model contradictions
Try it https://t.co/fBrh6UGKz7
The Gemini 2.0 Flash Thinking update includes a one-million-token context window, which greatly exceeds the previous 32,000 tokens. This allows the model to process large volumes of data, such as codebases or scientific articles. In addition, the model now supports code execution in its responses, expanding its capabilities for programming and computational tasks.
The updated version also generates longer responses, which is useful for detailed explanations or creative tasks. The frequency of contradictions in the model’s answers has been reduced, improving consistency between intermediate thoughts and final responses.
Gemini 2.0 Flash Thinking is available for free testing in Google AI Studio and via API. Users can enable code execution through the settings in the platform’s sidebar.
