An introduction to Google Gemini
![Google Gemini final keyword header](/static/img/final_keyword_header.width-1200.png)
What is Google Gemini
Google's Largest and Most Capable AI Model,Gemini is built from the ground up for multimodality — reasoning seamlessly across text, images, video, audio, and code.
Meet the first version of Gemini — our most capable AI model.
![Google Gemini final keyword header](/static/img/geminiultra90.png)
![Google Gemini final keyword header](/static/img/textgemini90.png)
Gemini surpasses SOTA performance on all multimodal tasks.
![Google Gemini Gemini surpasses SOTA performance on all multimodal tasks](/static/img/gemini59.png)
Gemini comes in three sizes
![Google Gemini Three sizes Google Gemini Three sizes](/static/img/three_size.png)
Gemini is natively multimodal, which gives you the potential to transform any type of input into any type of output.
![Gemini can generate code based on different inputs you give it Gemini can generate code based on different inputs you give it](/static/img/3.png)
![Gemini can generate text and images, combined Gemini can generate text and images, combined](/static/img/1.png)
![Gemini can reason visually across languages. Gemini can reason visually across languages.](/static/img/2.png)
Hands-on with Gemini
![Gemini can generate code based on different inputs you give it Gemini can generate code based on different inputs you give it](/static/img/3.png)