Google makes Interactions API the default interface for Gemini models and agents

2026-06-22 · Source: The Decoder · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Robotics & Autonomous Systems · Depth: Intermediate, quick

Summary

Google DeepMind has made its Interactions API the default interface for Gemini models and agents, moving it from beta (since December 2025) to general availability on June 22, 2026. This new API replaces the `generateContent` interface in Google AI Studio and documentation, though the old API remains functional. Future agent features will exclusively ship through the Interactions API, which Google's Logan Kilpatrick states "Interactions sets the stage for the new era of Agents." Key additions include Managed Agents with Linux sandboxes for background execution, multi-tool chaining with Google Search and Maps, and media generation capabilities for images, music, and speech. The schema has been simplified, replacing "user" and "model" roles with typed steps, and developers can now choose between Flex mode for a 50 percent cost reduction or Priority mode for optimized speed.

Key takeaway

For AI Engineers developing with Gemini, you should prioritize migrating to the new Interactions API to access future agent features. This transition is crucial for accessing advanced capabilities like Managed Agents, multi-tool chaining, and media generation. Evaluate your current `generateContent` implementations and consult the migration guide to ensure your applications remain compatible and benefit from the latest enhancements, including the choice between Flex mode for cost savings or Priority mode for speed.

Key insights

The Interactions API is Google's new standard for Gemini agents, enabling advanced features and flexible cost/speed options.

Principles

• Agent-centric design is Google's future direction.
• API evolution prioritizes new agent capabilities.
• Cost and speed optimization are configurable options.

In practice

• Select Flex mode for 50 percent cost reduction.
• Utilize Managed Agents for background tasks.
• Chain tools like Search and Maps for complex queries.

Topics

• Interactions API
• Gemini Agents
• Tool Chaining
• Managed Agents
• API Migration
• Cost Optimization

Best for: AI Architect, CTO, VP of Engineering/Data, AI Engineer, Machine Learning Engineer, Software Engineer

Related on AIssential

• Interactions API: our primary interface for Gemini models and agents — Google's Interactions API unifies Gemini model and agent interactions, enabling complex, stateful, and multimodal AI applications.
• Google's Managed Agents API promises one-call deployment at the cost of execution layer control — Google's Managed Agents centralize AI agent orchestration and execution, simplifying deployment but raising concerns about control and predictability.
• How to use Deep Research with the Gemini API — The Gemini Deep Research Agent automates complex research tasks, offering collaborative planning and multimodal input.
• Google Cloud Next ’26 Recap: Welcome to the era of agents — AI agents are transforming work by autonomously performing tasks at scale, supported by new platforms and infrastructure.
• Multimodal Function Calling with Gemini 3 and Interactions API — Multimodal function calling allows AI agents to natively process images returned by tools, enhancing visual understanding.
• 😺 Google just put agents in everything — Google is integrating Gemini agents as an operating layer across its ecosystem to transition AI from answering queries to executing actions.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The Decoder.