tokenstat
tokenstat

NVIDIA: Nemotron 3 Super 120B A12B

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B · rates as of · How this catalog is built · Benchmarks

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

Cheapest input
$0.05
$/MTok · models.dev
Cheapest output
$0.25
$/MTok
Context
1.0M
tokens
Sources
3
18 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (3 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
models.devcheapestnvidia/nemotron-3-super-120b-a12bNanoGPT$0.05$0.25$0.025262K
models.devcheapestnvidia/nemotron-3-super-120b-a12b:thinkingNanoGPT$0.05$0.25$0.025262K
models.devnvidia/nemotron-3-super-120b-a12bKilo Gateway$0.075$0.4$01.0M
models.devdeepinfra/nemotron-3-super-120b-a12bEden AI$0.085$0.4$0262K
LiteLLMnvidia/NVIDIA-Nemotron-3-Super-120B-A12BN/A$0.085$0.4$0.0085N/A
LiteLLMNVIDIA-Nemotron-3-Super-120B-A12BN/A$0.085$0.4$0.0085N/A
LiteLLMdeepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12BN/A$0.085$0.4$0.0085N/A
models.devnemotron-3-super-120b-a12bKenari$0.0971$0.48$0.0097262K
models.devnvidia-nemotron-3-super-120b-a12bRequesty$0.1$0.5$0262K
models.devnvidia/nemotron-3-super-120b-a12bVercel AI Gateway$0.15$0.65$0256K
models.devnvidia/nemotron-3-super-120b-a12bPerplexity$0.25$2.50$01M
models.devnebius/nvidia/nemotron-3-super-120b-a12bEden AI$0.3$0.9$0.3262K
models.devnvidia/nemotron-3-super-120b-a12bNebius$0.3$0.9$0.06262K
models.devnvidia/NVIDIA-Nemotron-3-Super-120B-A12BCrusoe$0.3$2.40$0.15262K
OpenRouternvidia/nemotron-3-super-120b-a12bOpenRouter$0.3$2.40$0.151.0M
LiteLLMnemotron-3-super-120b-a12bN/A$0.3$0.9$0.03N/A
LiteLLMnvidia/nemotron-3-super-120b-a12bN/A$0.3$0.9$0.03N/A
models.devarkanecloud/nvidia/nemotron-3-super-120b-a12bEden AI$0.4$0.8$0.1256K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-06Released: 2026-03-11Output limit: 262K tokensFamily: nemotron

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.