By Ken Muthomi - Reporter
U.S June 23, 2026 - Google has announced the general availability of its Interactions API, positioning it as the primary interface for building applications and agents powered by its Gemini models.
In a statement, Google confirmed that 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 has said that the API has gained rapid adoption among developers, as it features expanded capabilities that are engineered to power more advanced agentic workflows.
"With this GA release, the API now has a stable schema, and we also added major new capabilities that developers asked for, including Managed Agents, background execution, Gemini Omni (soon), and more," Google stated.
"All of our documentation now defaults to Interactions API, and we are working with ecosystem partners to make it the default interface across 3P SDKs and libraries," it added.
Some notable updates that have been made to the API include the introduction of Managed Agents, a feature that allows developers to provision a remote Linux sandbox through a single API call.
According to the tech giant, these agents have the capability to reason, execute code, browse the web, and manage files. The default agent, Antigravity, is included out of the box, and developers can also build custom agents with specific instructions, skills, and data sources.
The API also introduced background execution, enabling long-running tasks to be processed asynchronously by setting.
More from Kenya
Furthermore, the company has adjusted the tool integrations, allowing developers 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 offering collaborative planning, native charts and infographics, and multimodal grounding with images, PDFs, and audio.
The system also supports image creation via Nano Banana 2, music generation through Lyria 3, and expressive multi-speaker text-to-speech, according to Google.
Furthermore, the tech giant has introduced cost and performance tiers, including a Flex option that reduces costs by up to 50% for latency-tolerant workloads. Developers also get improved debugging tools, including more precise error reporting and extended interaction retention for up to 55 days on paid plans.
"The Interactions API is now the default for Google AI Studio, the Gemini API, and all our documentation, which includes a toggle to switch snippets back to the legacy format. We recommend using the Interactions API for all new projects and applications," Google stated.
To support adoption of the system, Google is also introducing a "gemini-interactions-api skill" designed to help coding agents stay updated with best practices, including streaming, function calling, structured outputs, and Deep Research workflows.