Key Facts

• The Interactions API has reached general availability and is now the primary API for interacting with Gemini models and agents, offering a unified endpoint with server-side state, background execution, tool combination, and multimodal generation.
• The API was launched in public beta in December 2023 and quickly became developers' favorite way to build applications with Gemini, with a stable schema and new capabilities added for the general availability release.
• The Interactions API allows developers to interact with Gemini models and agents using a few lines of code, with features such as passing a model ID for inference, an agent ID for autonomous tasks, and setting background=True for long-running tasks.
• The legacy generateContent API will remain fully supported, but frontier capabilities for long-running models and agents are expected to increasingly land exclusively on the Interactions API, which is designed for stateful, agentic workflows.
• The Interactions API is available through the Python and JavaScript SDKs, and developers can start using it with supported partners such as LiteLLM, Eigent, or Agno, and can access the API documentation and migration guide to get started.