Skip to main content
Back to Explore

Qwen3 30B A3B (Reasoning)

Alibaba·Released 2025-04-28
Open Source

Pricing

Input

$0.09

per 1M tokens

Output

$0.45

per 1M tokens

Blended

$0.18

per 1M tokens

Cheaper than 72% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.18

Monthly

$5.40

vs. Similar Models

Devstral Small (Jul '25)Q:0.0
$0.15-17%
Perplexity: Sonar ProQ:0.0
$6.00+3233%
QwQ 32B-PreviewQ:-0.1
$0.14-25%
Perplexity: SonarQ:+0.2
$1.00+456%

Performance

114

tokens/sec

Faster than 60% of models

1.08

seconds

Faster than 51% of models

18.68

seconds

Faster than 27% of models

Market Median

94 tok/s

21% faster

Median TTFT

1.10s

2% faster

Throughput/Dollar

631

tok/s per $/1M

Speed Comparison

LFM2 24B A2B
114 tok/s+0%
Qwen3 30B A3B (Non-reasoning)
112 tok/s-1%
DeepSeek V4 Flash
112 tok/s-1%

Benchmarks

MMLU-Pro
77.7%
GPQA Diamond
61.6%
HLE
6.6%
LiveCodeBench
50.6%
SciCode
28.5%
TerminalBench Hard
2.3%
MATH-500
95.9%
AIME
75.3%
AIME 2025
72.3%
IFBench
41.5%
Long Context Recall
0.0%
Tau2
26.0%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models