NVIDIA: Nemotron 3 Ultra - API in Egypt, billed in EGP
Livenemotron-3-ultra-550b-a55bNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it
Modality
Chat
Context window
203K tokens
Max output
183K tokens
Region
US
Published
29 Sept 2026
Pricing
Input
34.38
EGP per 1M tokens
Output
137.52
EGP per 1M tokens
Monthly cost example
3,781.9 EGP
Illustrative estimate: 50M input + 15M output tokens per month at this model's catalog rates.
Use it via the API
NVIDIA: Nemotron 3 Ultra works with any OpenAI-compatible SDK — point the base URL at https://dev-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://dev-backend.sovereigneg.com/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="nemotron-3-ultra-550b-a55b",
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://dev-backend.sovereigneg.com/v1",
apiKey: "YOUR_API_KEY",
})
const response = await client.chat.completions.create({
model: "nemotron-3-ultra-550b-a55b",
messages: [
{ role: "user", content: "What are some fun things to do in Cairo?" },
],
})
console.log(response.choices[0].message.content)curl https://dev-backend.sovereigneg.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nemotron-3-ultra-550b-a55b",
"messages": [
{"role": "user", "content": "What are some fun things to do in Cairo?"}
]
}'Frequently asked questions
How much does NVIDIA: Nemotron 3 Ultra cost?
34.38 EGP per 1M input tokens; 137.52 EGP per 1M output tokens. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.
What is the context window of NVIDIA: Nemotron 3 Ultra?
NVIDIA: Nemotron 3 Ultra supports a context window of 202,800 tokens (203K), with up to 182,520 output tokens per response.
Where is NVIDIA: Nemotron 3 Ultra hosted?
NVIDIA: Nemotron 3 Ultra is served from US (US-hosted inference).
How do I use NVIDIA: Nemotron 3 Ultra via the API?
NVIDIA: Nemotron 3 Ultra is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://dev-backend.sovereigneg.com/v1 and call /v1/chat/completions with model "nemotron-3-ultra-550b-a55b" and your API key.
Related models
View all models →llama-nemotron-embed-vl-1b-v2
NVIDIA · Embedding · 10K context
0.57 EGP / 1M input tokens
nemotron-3-nano-30b-a3b
NVIDIA · Chat · 262K context
2.87 EGP / 1M input tokens
nemotron-content-safety-3.5
NVIDIA · Chat · 131K context
11.46 EGP / 1M input tokens
nvidia-nemotron-3-super-120b-a12b
NVIDIA · Chat · 262K context
4.87 EGP / 1M input tokens