Cosmos 3 (Nano / Super): model ids and price

How to call it

3 ways to use Cosmos 3 (Nano / Super), with the model id each provider expects.

Providers, model ids, endpoints and docs for Cosmos 3 (Nano / Super)
Provider	Model id	Docs
Hugging Face	`nvidia/Cosmos3-Nano`	huggingface.co
Hugging Face	`nvidia/Cosmos3-Super`	huggingface.co
GitHub		research.nvidia.com github.com

Pricing

Price not published.

No price source linked. Checked 29 September 2026.

Specs

Input: Text, images, video, audio and robot actions
Output: Text, images, video, audio and robot actions
Context window: Not published
Max output: Not published
Open weights: Yes
Licence: OpenMDW-1.1 (commercial and non-commercial use)
Released: 1 June 2026
Status: Current
Type: World model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

Unified omni world model (generation + reasoning + action)

First

One Mixture-of-Transformers model (autoregressive + diffusion) replaces separate Cosmos Predict, Transfer, Reason and Policy models: world generation, physical reasoning, forward/inverse dynamics and action/policy generation.

Source: nvidianews.nvidia.com
Open omnimodal I/O

Inputs text, images, short video, audio and action trajectories (16-400 frames); outputs text, images, video (5-400 frames), 48 kHz stereo audio and actions (JSON).

Source: huggingface.co
Leaderboard results

Found after launch

NVIDIA cites best open text-to-image and image-to-video models on Artificial Analysis and best policy model on RoboArena.

Source: nvidia.com

Notes

Announced at GTC 2026-03-16 (‘the first world foundation model unifying synthetic world generation, vision reasoning and action simulation’ - NVIDIA claim); weights published 2026-05-31/06-01 (HF blog ‘The First Open Omni-model for Physical AI Reasoning and Action’). Sizes: Nano 16B, Super 64B. Linux + Ampere/Hopper/Blackwell GPUs, BF16. Technical report dated 2026-06-22.

Sources: HF blog, Cosmos3-Nano, Cosmos3-Super, technical report.