Tag
Google releases Gemini 3.1 Flash Lite for image generation (GA) and Gemini Omni Flash API preview for multi-turn conversational video editing at $0.10/sec.
Google DeepMind introduces the Interactions API to pair models like Nano Banana 2 Lite for image generation and Gemini Omni Flash for animation, enabling sequential edits with session history.
The Interactions API now supports background=True for async agent tasks, allowing long-running operations beyond HTTP timeouts. A guide explains usage, reconnection, and streaming.
Google's Interactions API for Gemini models and agents is now generally available, introducing managed agents, background execution for long-running tasks, and upcoming Gemini Omni support.