NVIDIA
Nemotron — enterprise-grade, hardware optimized
2
Models
$0.05
Cheapest Input
32K
Max Context
Pricing
Input
$0.10 / 1M tokens
Output
$0.50 / 1M tokens
Context Window
32K tokens
Max Completion
8.192K tokens
Supported Features
✓ Streaming✓ Open Weights✓ NVIDIA Optimized
Supported Parameters
temperaturetop_pstopmax_tokensInput Modalities
text
Output Modalities
text
Release: 2026-02
API Usage
curl https://api.stackai.one/v1/chat/completions \
-H "Authorization: Bearer sk-your-key" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3-super-120b-a12b",
"messages": [{"role": "user", "content": "Create a 4-core VM"}],
"temperature": 0.7,
"max_tokens": 4096
}'