Hormouz AIHormouzSign in

NVIDIA: Nemotron 3 Super: AI model

NVIDIA's Nemotron 3 Super is a 120B-parameter open hybrid Mamba-Transformer model that activates just 12B parameters, built for complex multi-agent applications. Reachable from inside Iran through Hormouz.

Context window:
262,144 tokens
Input:
$0.08/1M tokens
Output:
$0.45/1M tokens
Type:
text
  • Tools
  • Streaming
  • Long context

Thinking levels: medium · low

Nemotron 3 Super is a 120B-parameter open hybrid Mamba-Transformer Mixture-of-Experts (MoE) model from NVIDIA that activates only about 12B parameters per step for maximum compute efficiency and accuracy in complex multi-agent applications. With multi-token prediction it delivers higher token generation than many leading open models.

A standout feature is its very large context window, designed for long-term agent coherence, cross-document reasoning and multi-step task planning. The model is fully open. Weights, datasets and recipes are available. So it can be customized for secure deployment. Through Hormouz it is served behind an OpenAI-compatible API. Point your base URL at Hormouz and drop in a Hormouz key. Pricing is usage-based: $0.30 per million input tokens and $0.90 per million output tokens.

Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-super-120b-a12b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorNVIDIA
TypeText
Context window262,144 tokens
Pricing$0.08/M in · $0.45/M out
APIChat Completions
CapabilitiesStreaming · Tools

Benchmarks

12.8
Intelligence Index
Better than 21% of models we compared
37.7
Coding Index
Better than 39% of models we compared
1.7
Agentic Index
Better than 25% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
80%
HLE
Humanity's Last Exam
20.8%
IFBench
Instruction-following
71.5%
AA-LCR
Long-context reasoning
65.7%
CritPt
Research-level physics reasoning
3.1%
AA Omniscience
Broad factual knowledge accuracy
24.3%
Non-Hallucination
Rate of avoiding fabricated answers
13%

Coding

SciCode
Python for scientific computing
36.2%
Terminal-Bench Hard
Agentic coding & terminal use
28.8%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
67.8%
GDPval
Economically valuable tasks
0%

Source: Artificial Analysis

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-super-120b-a12b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="nvidia/nemotron-3-super-120b-a12b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "nvidia/nemotron-3-super-120b-a12b",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the NVIDIA: Nemotron 3 Super API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches NVIDIA: Nemotron 3 Super and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Nemotron 3 Super cost?
Billing is usage-based: $0.30 per million input tokens and $0.90 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Nemotron 3 Super from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Nemotron 3 Super compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What context window does Nemotron 3 Super have?
The model supports a very large context window, designed for long-term agent coherence, cross-document reasoning and multi-step task planning.
What are the capabilities of Nemotron 3 Super?
It uses a hybrid Mamba-Transformer Mixture-of-Experts architecture and supports tool calling, structured output and a reasoning mode.
What is Nemotron 3 Super good for?
It is a fit for complex multi-agent applications, multi-step planning and reasoning across several long documents. Especially where you need long-term agent coherence.

Updated 2026-10-13