Skip to main content
AI Models/NVIDIA
NVIDIA

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

StreamingOpen WeightsNVIDIA Optimized

Supported Parameters

temperaturetop_pstopmax_tokens

Input 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
  }'

Integrate NVIDIA into Your Cloud

Add NVIDIA models to your StackAI platform. Your customers get AI-powered cloud management instantly.