token.app › NVIDIA › Nemotron 3 Super (free)

Nemotron 3 Super (free) pricing & benchmarks

Nemotron 3 Super (free) is available from NVIDIA at Free per million input tokens and Free per million output tokens (Free blended at 3:1). It accepts up to 262,144 tokens of context. NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Pricing

Per million tokens · OpenRouter

InputFree

OutputFree

Blended (3:1)Free

Specification

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

Context window262K

Max output262K

ReleasedMar 2026

LicenceOpen weights

Modalitiesin:text, out:text

No independently-run benchmark scores are published for Nemotron 3 Super (free) yet. We show nothing rather than reprinting an unverified figure.

Compare Nemotron 3 Super (free)

Nemotron 3 Super (free) vs Qwen3.8 Max Nemotron 3 Super (free) vs DeepSeek V4 Flash 0731 Nemotron 3 Super (free) vs Claude Opus 5 Nemotron 3 Super (free) vs Gemini 3.6 Flash Nemotron 3 Super (free) vs Kimi K3 Nemotron 3 Super (free) vs GPT-5.6 Luna Nemotron 3 Super (free) vs GPT-5.6 Terra Nemotron 3 Super (free) vs GPT-5.6 Sol

FAQ

How much does Nemotron 3 Super (free) cost?

Nemotron 3 Super (free) costs Free per million input tokens and Free per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to Free per million tokens.

What is Nemotron 3 Super (free)'s context window?

Nemotron 3 Super (free) accepts up to 262,144 tokens of context, and can generate up to 262,144 output tokens.