Back to Models

NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b

Description

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...

API Usage Examples

OpenAI Compatible Endpoint

Use this endpoint with any OpenAI-compatible library. Model: NVIDIA: Nemotron 3 Super (nvidia/nemotron-3-super-120b-a12b)

curl https://api.ridvay.com/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer YOUR_API_KEY"   -d '{
    "model": "nvidia/nemotron-3-super-120b-a12b",
    "messages": [
      {
        "role": "user",
        "content": "Explain the capabilities of the NVIDIA: Nemotron 3 Super model"
      }
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

Supported Modalities

  • Text

API Pricing

  • Input: 0.1$ / 1M tokens
  • Output: 0.5$ / 1M tokens

Token Limits

  • Max Output: 262,144 tokens
  • Max Context: 262,144 tokens

Subscription Tiers

  • free
  • pro
  • ultimate