Last refreshed 2026-06-01. Next refresh: weekly.
Why use Cosmos 3 Super on NVIDIA NIM?
NVIDIA NIM offers Cosmos 3 Super with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: cosmos3-reasoner-supercosmos3-reasoner-superRequest example
cosmos3-reasoner-super.Gotchas
- Use provider model ID "cosmos3-reasoner-super", not the LLMReference slug "cosmos-3-super".
Pricing
| Type | Price (per 1M) |
|---|---|
| Image input | $1.00 |
| Video input | $1.00 |
| Audio input | $1.00 |
Capabilities
About Cosmos 3 Super
Cosmos 3 Super is NVIDIA's flagship 64B-parameter omnimodel for physical AI, designed for large-scale synthetic data generation and high-fidelity simulation on NVIDIA Hopper and Blackwell datacenter GPUs. Architecture: dual-tower Mixture-of-Transformers with a 32B autoregressive Reasoner and a 32B diffusion-based Generator. Supports 256K token reasoning context, 720p video generation at variable frame rates, and 10+ robot embodiment action domains. Ranked #1 among open models on Physics-IQ, PAI-Bench, R-Bench, RoboLab, RoboArena, VANTAGE-Bench, TAR, and Artificial Analysis image/video leaderboards (Computex 2026). Training data: 1.3B data points across 393 datasets (2024-2026). Inference performance (vLLM-Omni): ~55s for 50-step video on 8xH200.