Skip to main content
Back to Explore

NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

NVIDIA·Released 2025-08-18
Open Source

Pricing

Input

$0.05

per 1M tokens

Output

$0.20

per 1M tokens

Blended

$0.09

per 1M tokens

Cheaper than 86% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.09

Monthly

$2.58

vs. Similar Models

Gemma 3 27B InstructQ:0.0
$0.14+69%
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)Q:0.0
$0.09+2%
Qwen3 8B (Reasoning)Q:0.0
$0.37+330%
Mistral Large 2407Q:-0.1
$3.00+3388%

Performance

145

tokens/sec

Faster than 71% of models

1.24

seconds

Faster than 42% of models

1.24

seconds

Faster than 61% of models

Market Median

94 tok/s

54% faster

Median TTFT

1.11s

12% slower

Throughput/Dollar

1687

tok/s per $/1M

Speed Comparison

OpenAI: o3
145 tok/s+0%
Qwen: Qwen3.5-122B-A10B
145 tok/s-0%
Qwen3 30B A3B 2507 (Reasoning)
146 tok/s+1%

Benchmarks

MMLU-Pro
73.9%
GPQA Diamond
55.7%
HLE
4.0%
LiveCodeBench
70.1%
SciCode
20.9%
TerminalBench Hard
0.8%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
62.3%
IFBench
27.1%
Long Context Recall
22.7%
Tau2
23.4%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models