Nemotron 3 Super 120B
Experimentalvichar-nemotron-3-super
NVIDIA Nemotron 3 Super 120B, a large sparse reasoning model. Experimental: availability and rate limits may vary.
- Context window
- 262k
- Max output
- 236k
- Input
- $0.15 /M tokens
- Output
- $0.60 /M tokens
Supported parameters
- temperature
- max_tokens
- top_p
- response_format
- reasoning_effort
- tools
- tool_choice
- reasoning
curl https://api.vichar.io/v1/chat/completions \
-H "Authorization: Bearer $VICHAR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "vichar-nemotron-3-super",
"messages": [{"role": "user", "content": "Hello"}]
}'