Model Terminal

NVIDIA Nemotron 3 Super (120B-A12B)

NVIDIA Nemotron 3 Super is an open-weight hybrid Mamba-Transformer MoE reasoning model with 120B total parameters and only 12B active parameters, designed for efficient agentic AI workflows with a 1M-token context window. It targets multi-agent use cases such as software development, cybersecurity triage, and IT automation. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Peer value bars

Identity

Developer
NVIDIA
Openness
Modalities
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed