cosmos3-super
Coming soonCosmos3 is a world foundation model that unifies understanding and generation within a single Mixture-of-Transformer (MoT) architecture. Two tightly coupled towers—a Reasoner (vision-language model) and a Generator (world simulator)—share latent representations so that structured perception directly grounds realistic, temporally consistent simulation.
Modality
Chat
Region
US
Published
Jul 21, 2026
Use it via the API
cosmos3-super works with any OpenAI-compatible SDK — point the base URL at https://preprod-backend.sovereigneg.com/v1 and use your SovereignEG API key.
Run inference
OpenAI-compatible — POST /v1/chat/completions — drop-in for any OpenAI SDK.
from openai import OpenAI
client = OpenAI(
base_url="https://preprod-backend.sovereigneg.com/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="cosmos3-super",
messages=[
{"role": "user", "content": "What are some fun things to do in Cairo?"}
],
)
print(response.choices[0].message.content)import OpenAI from "openai"
const client = new OpenAI({
baseURL: "https://preprod-backend.sovereigneg.com/v1",
apiKey: "YOUR_API_KEY",
})
const response = await client.chat.completions.create({
model: "cosmos3-super",
messages: [
{ role: "user", content: "What are some fun things to do in Cairo?" },
],
})
console.log(response.choices[0].message.content)curl https://preprod-backend.sovereigneg.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "cosmos3-super",
"messages": [
{"role": "user", "content": "What are some fun things to do in Cairo?"}
]
}'Frequently asked questions
Where is cosmos3-super hosted?
cosmos3-super is served from US (US-hosted inference).
How do I use cosmos3-super via the API?
cosmos3-super is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://preprod-backend.sovereigneg.com/v1 and call /v1/chat/completions with model "cosmos3-super" and your API key.
Related models
View all models →llama-nemotron-embed-vl-1b-v2
NVIDIA · Embedding · 10K context
0.56 EGP / 1M input tokens
nemotron-3-nano-30b-a3b
NVIDIA · Chat · 262K context
2.81 EGP / 1M input tokens
nemotron-content-safety-3.5
NVIDIA · Chat · 131K context
11.24 EGP / 1M input tokens
nvidia-nemotron-3-super-120b-a12b
NVIDIA · Chat · 262K context
4.78 EGP / 1M input tokens