token.app › NVIDIA › Nemotron 3 Super

Nemotron 3 Super pricing & benchmarks

Nemotron 3 Super is available from NVIDIA at $0.300 per million input tokens and $2.40 per million output tokens ($0.825 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
Input$0.300
Output$2.40
Blended (3:1)$0.825
Specification
nvidia/nemotron-3-super-120b-a12b
Context window262K
Max output236K
ReleasedMar 2026
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for Nemotron 3 Super yet. We show nothing rather than reprinting an unverified figure.
Where to run Nemotron 3 Super
3 hosts · 5.0× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
HostBlended $/1MIn / OutContextWeightsUptime 24h
DeepInfra $0.164 $0.085 / $0.400 262K bf16 99.9%
DekaLLM $0.172 $0.080 / $0.450 262K fp8 99.9%
Crusoe $0.825 $0.300 / $2.40 262K fp8 100.0%
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Nemotron 3 Super
FAQ
How much does Nemotron 3 Super cost?
Nemotron 3 Super costs $0.300 per million input tokens and $2.40 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.825 per million tokens.
What is Nemotron 3 Super's context window?
Nemotron 3 Super accepts up to 262,144 tokens of context, and can generate up to 235,929 output tokens.