nvidia Open weights Reasoning

Nemotron 3 Nano 30B A3B pricing & benchmarks

Released Dec 14, 2025 · served by 3 providers

Input / 1M tokens$0.050
Output / 1M tokens$0.200
Context window262K
Cached input
Intelligence index14.2
Coding index14.4
Agentic index2.0
1M in + 300K out$0.11

What Nemotron 3 Nano 30B A3B is

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...

Providers and prices for Nemotron 3 Nano 30B A3B

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Crusoecheapest $0.050 $0.200 262K fp8 100.0%
DeepInfra $0.050 $0.200 262K fp4 99.2%
Novita $0.050 $0.200 262K fp4 94.2%

Cheaper models in the same class

Models scoring within 4 points of Nemotron 3 Nano 30B A3B on the Intelligence Index, but with a lower output price.

FAQ

How much does the Nemotron 3 Nano 30B A3B API cost?

$0.050 per 1M input tokens and $0.200 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.11.

Is Nemotron 3 Nano 30B A3B free?

No. It is a paid model starting at $0.050 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Nemotron 3 Nano 30B A3B?

Crusoe at $0.050 input / $0.200 output per 1M tokens (fp8 quantization).

Can I self-host Nemotron 3 Nano 30B A3B?

Yes — weights are published as nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 on Hugging Face, so you can run it on your own hardware.