token.app โ€บ NVIDIA โ€บ Nemotron 3 Super

Nemotron 3 Super pricing & benchmarks

Nemotron 3 Super is available from NVIDIA at $0.085 per million input tokens and $0.400 per million output tokens ($0.164 blended at 3:1). It accepts up to 1,000,000 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 ยท OpenRouter
Input$0.085
Output$0.400
Blended (3:1)$0.164
Specification
nvidia/nemotron-3-super-120b-a12b
Context window1M
Max output16K
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 ยท 2.7ร— between cheapest and dearest. Blended at 3:1. โš  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
โš  262K context, not 1M
$0.164 $0.085 / $0.400 262K bf16 91.7%
DigitalOcean $0.213 $0.165 / $0.358 1M โ€” 95.9%
Nebius
โš  262K context, not 1M
$0.450 $0.300 / $0.900 262K fp4 96.1%
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 โ€” the score above is not host-specific.
Compare Nemotron 3 Super
FAQ
How much does Nemotron 3 Super cost?
Nemotron 3 Super costs $0.085 per million input tokens and $0.400 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.164 per million tokens.
What is Nemotron 3 Super's context window?
Nemotron 3 Super accepts up to 1,000,000 tokens of context, and can generate up to 16,384 output tokens.