computetrail

All models ·nvidia

NVIDIA: Nemotron 3 Super

Provider: nvidia · nvidia/nemotron-3-super-120b-a12b

Input
$0.085 /1M
Output
$0.4 /1M
Context
1,000,000 tokens

How NVIDIA: Nemotron 3 Super pricing compares

At $0.4 / 1M output tokens, NVIDIA: Nemotron 3 Super is the 3rd-cheapest of 5 nvidia models we track. It's cheaper than 84% of the 392 paid models on computetrail (64th-cheapest overall). Output costs 4.7× its input price ($0.085 / 1M in). For a typical 3:1 input-to-output workload that works out to about $0.16 / 1M blended. Its 1,000,000 tokens context window ranks 111th-largest of 392 models with a published limit.

Output price history

$0.900$0.40006-2907-2908-27

Across 60 daily snapshots since 2026-06-29, the output price has held steady at $0.4 / 1M — no change so far.

Similar-priced models

ModelProviderOutput $/1MContext
Meta: Llama 3.1 70B Instructmeta-llama$0.4131,072
DeepSeek: DeepSeek V3.2 Expdeepseek$0.41163,840
DeepSeek: DeepSeek V3.2deepseek$0.38163,840
Qwen: Qwen3 8Bqwen$0.455131,072
Meta: Llama 4 Scoutmeta-llama$0.341,310,720
Meta: Llama 3.2 3B Instructmeta-llama$0.33131,072

Prices are recorded daily from public provider data via OpenRouter and normalized to USD per 1M tokens. See methodology.