NVIDIA Nemotron Nano 9B V2 pricing

Cheapest host: DeepInfra · checked Oct 26, 2026
Benchmarks and alternatives →
$0.04 / $0.16per 1M tokens in / out

Price sheetper 1M tokens

Input$0.04DeepInfra
Output$0.16
Context · max output131K · 131Ktokens
Exact deepinfra deployment nvidia/NVIDIA-Nemotron-Nano-9B-v2; provider contract, not a family-wide guarantee. USD per million input tokens.

Where to buy2 providers · per 1M tokens

ProviderInputOutputContext
NVIDIAlab$0$0—
DeepInfra$0.04$0.16—

In NVIDIA's line-upper 1M in / out

Nemotron 3 Nano Omni 30B A3B Reasoning$0 / $0−100%
Nemotron 3.5 Lightning$0.025 / $0.12−30%
NVIDIA Nemotron Nano 9B V2$0.04 / $0.16this model
Nemotron 3 Nano 30B A3B$0.06 / $0.24+50%
Nemotron Nano 3 30B$0.06 / $0.24+50%
Nemotron 3.5 Super VL$0.06 / $0.35+89%
NVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4$0.08 / $0.452.5×
<

Cheaper for the same workvs NVIDIA Nemotron Nano 9B V2

Qwen3.5 4B thinkingOpen-14%score +92%$0.03 / $0.15
Nemotron 3.5 Lightning thinkingOpen-30%score +88%$0.079
GPT OSS 120B highOpen-14%score +70%$0.11
GPT OSS 20B lowOpen-49%score +45%$0.018 / $0.09
Granite 4.2 3B thinkingOpen-25%score +32%$0.006

Pricing questions

How much does NVIDIA Nemotron Nano 9B V2 cost?›

$0.04 per 1M input tokens and $0.16 per 1M output tokens.

Is NVIDIA Nemotron Nano 9B V2 free to use?›

There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.

What is a cheaper alternative to NVIDIA Nemotron Nano 9B V2?›

Qwen3.5 4B at thinking effort costs -14% per task with a score +92% on Humanity's Last Exam.