Skip to content

Nemotron 3 Super

text → textHugging Face OpenRouter Cost calculator →

Best price · blended / 1M

$0.125

at DeepInfra

Input / output
$0.06 / $0.32
Providers
2
Spread
1.88×
7 days
−20.0%
30 days
−23.7%
Context
256K
Prices per 1M tokens, blended: DeepInfra (bf16/flex) $0.125, DeepInfra $0.156, DekaLLM $0.173, DeepInfra (bf16/priority) $0.234.

Providers

  • DeepInfraCheapest
    bf16/flex
    $0.125
    $0.06 in · $0.32 out
    ref vs ref
    256K ctx100% uptimebf16
  • $0.156
    $0.075 in · $0.40 out
    +25% vs ref
    256K ctx99.6% uptimebf16
  • $0.173
    $0.08 in · $0.45 out
    +38% vs ref
    256K ctx33.9% uptimefp8
  • bf16/priority
    $0.234
    $0.113 in · $0.60 out
    +88% vs ref
    256K ctx91.5% uptimebf16
Blended = (3 × input + output) / 4. Ref $0.125 = median of cheapest 20%.

Price history

USD per 1M tokens · each step is a price change

Prices in USD / 1M tokens.

Changes

  • Now served,
    Listed
  • Now served,
    Listed
  • No longer served,
    Delisted
  • Input price,
    $0.085→$0.075−11.8%
  • Now served,
    Listed

About

The cheapest provider for Nemotron 3 Super is DeepInfra at $0.125 per 1M tokens (blended), charging $0.06 per 1M input and $0.32 per 1M output tokens. 2 providers serve it; the most expensive charges 1.88× the typical price. Its best price fell 23.7% over the last 30 days. Context window: 256K tokens. Prices tracked since Oct 3, 2026.

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...
Released
Mar 11, 2026
First tracked
Oct 3, 2026
Canonical slug
nvidia/nemotron-3-super-120b-a12b-20230311
Weights
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8