Google quietly published the ML Kit GenAI application programming interface (API) last week, enabling Android developers to create apps that take advantage of Gemini Nano’s capabilities.
As per a document added to its developer forum, the Mountain View-based tech giant is now letting developers access the image description feature of the artificial intelligence (AI) model as well. Previously, the model was only available for experimental use, and developers could not publish apps built using the large language model (LLM).
According to Android Authority, the tech giant has added a new support document to Gemini Nano’s Android developer web page. This website now refers to a new API called ML Kit GenAI, which will allow developers to “harness the power of Gemini Nano to deliver out-of-the-box performance for common tasks through a simplified, high-level interface.”
Developers can use the ML Kit GenAI API to access additional functionalities such as text summarization, message proofreading, message rewriting, and image brief descriptions.
Notably, Google has booked a session at I/O 2025 titled “Gemini Nano on Android: Building with on-device generation AI.” The company is anticipated to discuss the model’s capabilities and how developers may include the functionality into the apps they are developing.
Google originally made Gemini Nano available to developers in October 2024 as part of the AI Edge software developer kit (SDK). However, this was only offered as an experimental access, therefore, developers were unable to publish the apps created using the AI model.
Also Read:
Furthermore, the SDK only enables developing apps for the Google Pixel 9 series, whereas the new API supports building apps for all Android devices. The SDK only allowed text-based features, and the image description function was not available.
