Skip to main content
Back to Explore

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

NVIDIA·Released 2025-12-15
Open Source

Pricing

Input

$0.05

per 1M tokens

Output

$0.20

per 1M tokens

Blended

$0.09

per 1M tokens

Cheaper than 85% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.09

Monthly

$2.64

vs. Similar Models

Gemma 3 27B InstructQ:0.0
$0.14+65%
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)Q:0.0
$0.09-2%
Qwen3 8B (Reasoning)Q:0.0
$0.37+320%
Mistral Large 2407Q:-0.1
$3.00+3309%

Performance

85

tokens/sec

Faster than 45% of models

0.27

seconds

Faster than 98% of models

0.27

seconds

Faster than 99% of models

Market Median

94 tok/s

10% slower

Median TTFT

1.11s

76% faster

Throughput/Dollar

969

tok/s per $/1M

Speed Comparison

MiniMax: MiniMax M3
85 tok/s-0%
OpenAI: GPT-5.2
85 tok/s+0%
North Mini Code
85 tok/s+0%

Benchmarks

MMLU-Pro
57.9%
GPQA Diamond
39.9%
HLE
4.6%
LiveCodeBench
36.0%
SciCode
23.0%
TerminalBench Hard
12.1%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
13.3%
IFBench
37.5%
Long Context Recall
6.7%
Tau2
25.4%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models