Google has officially announced an update of the existing Gemini 2.5 Pro AI model with advanced coding features.
The Mountain View-based tech giant revealed on Tuesday, May 6, 2025, that the newer version of the model Gemini 2.5 Pro Preview (I/O edition) can create an interactive web app based on a single YouTube video.
The company stated that it had planned to launch this version at its upcoming Google I/O 2025 event, scheduled to be held between May 20-21.
However, positive feedback for the model made the tech giant to release it earlier.
Gemini 2.5 Pro gets update of enhanced coding capabilities
In a blog post, Google detailed the updated large language model, claiming that with improved code understanding, the Gemini 2.5 Pro (I/O edition) can even build interactive web apps from scratch.
Moreover, the model can perform other complex coding tasks, like code transformation, code editing, and developing complex agentic workflows.
To note, this functionality is currently only available in Google AI Studio.
According to Google, the AI model can be connected with an integrated development environment (IDE) and inspect components to match style properties such as colours, fonts, padding, margins, and more.
It is worth noting that developers can access and begin vibe coding with the updated Gemini 2.5 Pro model in the Gemini application programming interface (API) via Google AI Studio and Vertex AI.
