Google announced the general availability of its Interactions API on June 23, 2026, positioning it as the primary interface for building applications and agents powered by its Gemini models. Developers can access the API through Python and JavaScript SDKs, or via partner platforms such as LiteLLM, Eigent, and Agno. Since its inception in December 2025, Google stated the API has gained rapid adoption among developers. With this GA release, the API now has a stable schema and added major new capabilities including Managed Agents, background execution, and Gemini Omni (soon). Managed Agents allow developers to provision a remote Linux sandbox through a single API call, with the default agent, Antigravity, included out of the box. Background execution enables long-running tasks to be processed asynchronously. The company adjusted tool integrations to combine built-in tools such as Google Search and Google Maps with custom functions in a single request. Other upgrades include improvements to Deep Research agents, image creation via Nano Banana 2, music generation through Lyria 3, and expressive multi-speaker text-to-speech. Google introduced cost and performance tiers, including a Flex option that reduces costs by up to 50% for latency-tolerant workloads, and improved debugging tools with extended interaction retention for up to 55 days on paid plans. Google stated the Interactions API is now the default for Google AI Studio, the Gemini API, and all documentation.