NVIDIA Cosmos

Open platform for building Physical AI with world models, datasets, and tools

AI ModelsOpen Source AIOpen sourceOpen source
Visit tool

nvidia.com

About NVIDIA Cosmos

NVIDIA Cosmos is an open platform that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more. It provides world models, datasets, and tools for building Physical AI. The platform supports various use cases, including robot learning, autonomous vehicle training, and video analytics.

Description summarised by AI from the sources listed below.

Key features

  • World understanding: Analyze videos and images for captions, temporal events, next actions, spatial grounding, physical plausibility, and causal outcomes
  • World generation: Produce images, videos, synchronized sound, and action-conditioned rollouts from text, image, video, or action inputs
  • Action modeling: Predict policy actions, inverse dynamics, and forward dynamics for robotics, camera motion, egocentric motion, and autonomous-driving settings

Use cases

  • Robot learning
  • Autonomous vehicle training
  • Video analytics

Pricing

Pricing model: Open source. Detailed plans are not recorded; check the official website for current prices.

Pricing from the tool's own website.