LLM Reference
NVIDIA NIM

Using Cosmos 3 Super on NVIDIA NIM

Implementation guide · Cosmos 3 · NVIDIA AI

ProvisionedOpen Weights

NVIDIA NIM exposes Cosmos 3 Super through model ID cosmos3-reasoner-super. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-01. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at NVIDIA NIM and generate an API key.
  2. 2
    Use the NVIDIA NIM SDK or REST API to call cosmos3-reasoner-super — see the documentation for request format.

Code Examples

See NVIDIA NIM documentation for integration details.

Pricing on NVIDIA NIM

TypePrice (per 1M)
Image input$1.00
Video input$1.00
Audio input$1.00

Capabilities

VisionMultimodalReasoningAudio

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.

Model Specs

Released2026-05-31
Parameters64B
Context256k
ArchitectureMixture of Transformers

Provider

NVIDIA NIM
NVIDIA NIM

NVIDIA

Santa Clara, California, United States