Cosmos 3 Super Image

Image Generation

cosmos-3-super-image

Nvidia|Created Oct 30, 2026

Image Generation

Cosmos3-Super-Text2Image is a post-trained text-to-image variant of the Cosmos3-Super base model. Cosmos3 is a collection of omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands, serving as a foundational building block for Physical AI applications and research.

Overview Specifications Activity Performance Uptime Examples API Reference

Compare

Code Example

Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.

Basic request example. Ensure API key permissions. For more details, see our documentation.

from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key="YOUR_API_KEY")

resp = client.images.generate(
    model="cosmos-3-super-image",
    prompt="A white siamese cat",
    size="1024x1024",
    n=1,
    response_format="url",
)
print(resp.data)