All Models
NVIDIA active

Nemotron 3 Super

nvidia/nemotron-3-super

MoE model (120B total, 12B active) optimized for text tasks with 262K context. Free tier.

Specifications

Context Window 262K tokens
Max Output 8.2K tokens
Latency fast
Knowledge Cutoff
Training Data

Pricing

Input $0.00 per 1M tokens
Output $0.00 per 1M tokens

Capabilities

text Text generation and understanding

API Identifiers

Model ID nvidia/nemotron-3-super
Provider API ID nvidia/nemotron-3-super

Usage via Multi-Router

curl https://api.multi-router.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "x-mr-router-id: YOUR_ROUTER_ID" \
  -d '{
    "model": "nvidia/nemotron-3-super",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'