Nvidia Nemotron 3 Super 120B

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

Nvidia's Nemotron 3 Super 120B A12B model from the March 2026 Nemotron 3 release. It uses a hybrid Mamba-Transformer MoE architecture and targets agentic and coding workloads with a 262K context window here.

Reasoning

Chat with this model Create an API key

Pricing

Includes our margin. Charged per request from your balance.

Input: $0.055 per 1M tokens
Output: $0.275 per 1M tokens
Typical message: $0.002

Details

Provider: NVIDIA
Context: 262K tokens
Max output: 16K tokens
Added: Mar 1, 2026

Use it from the API

Replace $HIDE_API_KEY with a key from the Developers page. Base URL https://hide.st/api/v1.

curl https://hide.st/api/v1/chat/completions \
  -H "Authorization: Bearer $HIDE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-super-120b-a12b",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Pricing

Details

Use it from the API

Search