Project Genie Integrations

Google AI Ultra is Google’s highest-tier AI subscription plan that provides maximum access to advanced Gemini models, AI-powered creative tools, agentic AI capabilities, developer platforms, and premium productivity features. Designed for power users, developers, creators, and enterprises, the plan includes significantly higher usage limits, Gemini Spark access, Project Genie, premium Google Flow credits, advanced coding tools, and cloud storage starting at 20 TB across Google services.

Genie 3 is DeepMind’s next-generation, general-purpose world model capable of generating richly interactive 3D environments in real time at 24 frames per second and 720p resolution that remain consistent for several minutes. Prompted by text input, the system constructs dynamic virtual worlds where users (or embodied agents) can navigate and interact with natural phenomena from multiple perspectives, like first-person or isometric. A standout feature is its emergent long-horizon visual memory: Genie 3 maintains environmental consistency over extended durations, preserving off-screen elements and spatial coherence across revisits. It also supports “promptable world events,” enabling users to modify scenes, such as changing weather or introducing new objects, on the fly. Designed to support embodied agent research, Genie 3 seamlessly integrates with agents like SIMA, facilitating goal-based navigation and complex task accomplishment.

Genie 4 is a generative AI world model developed by Google DeepMind that creates realistic, interactive virtual environments in real time. The model generates explorable worlds with dynamic visuals, native audio, physical interactions, and responsive human characters. Users can navigate generated environments using keyboard controls and modify scenes through natural language instructions, including changing weather conditions, moving cameras, and introducing objects. Its physics simulation capabilities model phenomena such as aerodynamics, collisions, and natural human movement. Genie 4 integrates with Google's Gemini models to support complex reasoning, multistep event simulation, and interactive environments that respond coherently to user actions. The model is available as a limited research preview for trusted testers, with planned access through Project Genie, Google AI Studio, and the Gemini API.