NVIDIAnemotron-3-super-120b-a12b

NVIDIA: Nemotron 3 Super API Pricing

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 ...

Base Input Price$0.075/ 1M tokens

Base Output Price$0.40/ 1M tokens

Prompt Cache Read$0.075-0% discount

Batch API RateN/A24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates

Provider Name	Input / 1M	Output / 1M	Prompt Caching	Access Endpoint
NVIDIA Direct	$0.075	$0.40	Not available	Connect
OpenRouter	$0.075	$0.40	Not available	Connect

Head-to-Head Comparisons for NVIDIA: Nemotron 3 Super

NVIDIA: Nemotron 3 Super vs OpenAI: GPT-6.1 Sol$0.075/M vs $2/M

NVIDIA: Nemotron 3 Super vs GPT-4o (Omni)$0.075/M vs $2.5/M

NVIDIA: Nemotron 3 Super vs Claude 3.5 Sonnet$0.075/M vs $3/M

NVIDIA: Nemotron 3 Super vs DeepSeek-V3 (deepseek-chat)$0.075/M vs $0.27/M