Brief IA

Google Enforces the Interactions API for its Gemini Models

💻 Code & Dev·Tom Levy·

Google Enforces the Interactions API for its Gemini Models

Google Enforces the Interactions API for its Gemini Models
Key Takeaways
1Google Deepmind has chosen the Interactions API as the default interface for its Gemini models.
2This API replaces the old generateContent API with a simplified schema based on typed steps.
3The new features for Gemini agents will be exclusively accessible through the Interactions API.
💡Why it mattersThis transition to a single API could standardize and simplify the development of Gemini agents, influencing developers and users of these technologies.
Le brief IA que lisent les pros

Le brief IA que les pros lisent chaque soir

Les 7 actus IA du jour, décryptées en 5 min. Gratuit.

Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.

Choisis ton rythme

Gratuit · Pas de spam · Désabonnement en 1 clic

📄
Full Analysis

Google Enforces the Interactions API for its Gemini Models

Google DeepMind has announced that the Interactions API is now the default interface for Gemini models and agents. This API, in beta since December 2025, is now generally available and replaces the old generateContent interface in Google AI Studio along with all associated documentation. The old API is still operational, but new features for agents will now only be accessible through the Interactions API. "Interactions paves the way for a new era of agents," writes Logan Kilpatrick, head of developer relations at Google. Google has released a migration guide to facilitate this transition.

Recent additions include:

  • Managed agents with their own Linux sandbox
  • Background execution for long-running tasks
  • Tool chaining with Google Search and Maps
  • Media generation for images, music, and speech

Google has also streamlined the schema since the beta version. The previous role structure with labels like "user" and "model" has now been replaced by typed steps, where each action, from user input to function calls, is defined as a distinct step. Developers can choose between Flex mode and Priority mode. Flex mode reduces costs by 50%, while Priority mode optimizes speed.

Brief IA — L'actualité IA en français

L'essentiel de l'actualité de l'intelligence artificielle, décrypté et expliqué chaque jour.