TokenCosts AI.iov1.0
Back to Models Directory
NVIDIAnemotron-3-nano-30b-a3b

NVIDIA: Nemotron 3 Nano 30B A3B API Pricing

Official PricingCall via OpenRouter

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

Base Input Price$0.060/ 1M tokens
Base Output Price$0.24/ 1M tokens
Prompt Cache Read$0.012-80% 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 NameInput / 1MOutput / 1MPrompt CachingAccess Endpoint
NVIDIA Direct$0.060$0.24SupportedConnect
OpenRouter$0.060$0.24SupportedConnect

Head-to-Head Comparisons for NVIDIA: Nemotron 3 Nano 30B A3B

NVIDIA: Nemotron 3 Nano 30B A3B vs OpenAI: GPT-6.1 Sol$0.06/M vs $2/M
NVIDIA: Nemotron 3 Nano 30B A3B vs GPT-4o (Omni)$0.06/M vs $2.5/M
NVIDIA: Nemotron 3 Nano 30B A3B vs Claude 3.5 Sonnet$0.06/M vs $3/M
NVIDIA: Nemotron 3 Nano 30B A3B vs DeepSeek-V3 (deepseek-chat)$0.06/M vs $0.27/M