Nemotron 3 Super

nvidia/nemotron-3-super

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.

Pricing

Specifications

Use Nemotron 3 Super

Point your existing OpenAI SDK at xKiro and pass nvidia/nemotron-3-super as the model. Nothing else in your code changes.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.xkiro.com/v1",
    api_key="YOUR_XKIRO_KEY",
)

response = client.chat.completions.create(
    model="nvidia/nemotron-3-super",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

max_tokens · temperature · top_p · stop · frequency_penalty · presence_penalty · seed · stream · tools · tool_choice · response_format · structured_outputs · reasoning · include_reasoning

Related models

• Llama 3.3 Nemotron Super 49B$0.1
• Nemotron 3 Nano$0.05
• Nemotron 3 Nano Omni$0.05
• Nemotron 3 Ultra$0.5
• Fable 5$10.00
• Opus 4.6$5.00