Skip to content
Vichar

Nemotron 3 Super 120B

NVIDIA's mid-size Nemotron 3 MoE model with 120B total and 12B active parameters, built for efficient reasoning and multi-agent applications.

nemotron-3-super-120bGet API key

Context window

262k

tokens

Max output

—

tokens

Input

$0.50

per 1M tokens

Output

$1.50

per 1M tokens

Quick start

1curl https://api.vichar.io/v1/chat/completions \
2  -H "Authorization: Bearer $VICHAR_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "nemotron-3-super-120b",
6    "messages": [{"role": "user", "content": "Hello"}]
7  }'

Supported parameters

  • temperature
  • max_tokens
  • top_p
  • frequency_penalty
  • presence_penalty
  • response_format
  • tools
  • tool_choice
  • reasoning