NVIDIA launches Cosmos 3, an open world model for physical AI
Cosmos 3 is NVIDIA's open foundation model aimed squarely at physical AI — helping robots and autonomous machines perceive and act in the real world rather than chat about it. NVIDIA bills it as the first fully open omnimodel with native reasoning across text, image, video, ambient sound, and action, trained on roughly 20 trillion tokens including nearly a billion images and hundreds of millions of videos. The Super and Nano variants ship now, alongside a Cosmos Coalition of robotics labs organized to advance open world models.
Why it matters: LLMs got to bootstrap on a near-infinite corpus of text the internet had already written; robotics has no such free lunch, because the real world doesn't come pre-labeled and collecting physical interaction data is slow and costly. A capable world model that can generate training data and robot policies attacks that scarcity directly, which is the actual bottleneck in the field. Making it open is the strategically interesting part — it mirrors how open LLMs collapsed the barrier to entry for software, letting small teams build on frontier capability instead of funding it. There's also a self-interested logic worth naming: NVIDIA wins if physical AI booms regardless of who trains the models, because the robots and their simulation pipelines run on its hardware. Seeding an open ecosystem and a coalition is how you accelerate an entire market you're positioned to sell into.