Gemini Omni Flash
Gemini Omni is Google’s new model family where Gemini’s ability to reason meets the ability to create, starting with video. The first model in the family, Gemini Omni Flash, can create anything from any input by combining images, audio, video, and text as input, then generating high-quality videos grounded in Gemini’s real-world knowledge. It gives users an easier way to edit video through conversation, where every instruction builds on the last, characters stay consistent, physics hold up, and the scene remembers what came before. Users can transform specific details or entire worlds, reimagine action, add new characters or objects, change environments, adjust camera angles, refine styles, and build multi-turn edits without losing the thread of the original scene. Gemini Omni is designed to bridge photorealism and meaningful storytelling by reasoning about what should happen next, using an intuitive understanding of forces like gravity, kinetic energy, and fluid dynamics.
Learn more
Gemini Robotics-ER 1.6
Gemini Robotics-ER 1.6 is a family of AI models developed by Google DeepMind to bring advanced multimodal intelligence into the physical world by enabling robots to perceive, reason, and act in real-world environments. Built on the Gemini 2.0 foundation, it extends traditional AI capabilities by adding physical action as an output modality, allowing robots to interpret visual input and natural language instructions and convert them directly into motor commands to complete tasks. It includes a vision-language-action model that processes images and instructions to execute tasks, as well as a complementary embodied reasoning model (Gemini Robotics-ER) that specializes in spatial understanding, planning, and decision-making within physical environments. These models enable robots to generalize across new situations, objects, and environments, allowing them to perform complex, multi-step tasks even if they were not explicitly trained for them.
Learn more
Gemini Robotics 2
Gemini Robotics 2 is Google DeepMind’s intelligence layer for adaptable robots, bringing whole-body control, advanced dexterity, embodied reasoning, and multi-robot collaboration to physical AI. It includes three models. Gemini Robotics 2 is a vision-language-action model that converts visual and language input into motor control, enabling humanoids and bi-arm robots to act from feet to fingertips. It can coordinate walking, crouching, reaching, balancing, and object manipulation, while controlling five-fingered hands or standard grippers for delicate and precise tasks. Gemini Robotics ER 2 serves as the high-level brain, communicating with people, understanding its surroundings, planning multi-step tasks that last several minutes, coordinating actions with the VLA, tracking progress, self-correcting failures, and allowing different robots to work together.
Learn more
Gemini 4 Argon
Gemini 4 Argon is a frontier artificial intelligence model developed by Google DeepMind for complex reasoning, software engineering, cybersecurity, and professional knowledge work. The model supports multimodal inputs, including text, images, audio, video, and PDF documents, with a unified context window of approximately one million tokens. Its advanced reasoning capabilities enable it to analyze difficult problems, maintain context across lengthy workflows, and execute multistep tasks. Gemini 4 Argon supports autonomous AI agents, code generation, application development, scientific research, and analysis of legal and financial information. Developer capabilities include function calling, code execution, structured outputs, search grounding, and preview support for computer use. The model is available through the Gemini API, Google AI Studio, Google Antigravity, and supported Gemini applications and enterprise services.
Learn more
