Skip to main content
Back to Explore

Qwen3 30B A3B 2507 Instruct

Alibaba·Released 2025-07-29
Open Source
Compare

Related Models

Qwen: Qwen3.7 Plus2026-06-03Qwen: Qwen3.7 Max2026-05-21Qwen: Qwen3.5 Plus 2026-04-202026-04-27Qwen: Qwen3.6 Flash2026-04-27Qwen: Qwen3.6 Max Preview2026-04-27Qwen3.6 27B (Non-reasoning)2026-04-22Qwen3.6 27B2026-04-21Qwen3.6 Max Preview2026-04-20

Pricing

Input

$0.15

per 1M tokens

Output

$0.40

per 1M tokens

Blended

$0.21

per 1M tokens

Cheaper than 68% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.21

Monthly

$6.39

vs. Similar Models

GLM-4.5V (Reasoning)Q:0.0
$0.90+323%
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)Q:0.0
$0.90+323%
Mistral Large 2 (Nov '24)Q:0.0
$3.00+1308%
Mistral Small 3.2Q:0.0
$0.13-40%

Performance

173

tokens/sec

Faster than 81% of models

1.03

seconds

Faster than 54% of models

1.03

seconds

Faster than 68% of models

Market Median

94 tok/s

85% faster

Median TTFT

1.10s

6% faster

Throughput/Dollar

813

tok/s per $/1M

Speed Comparison

Llama 3.1 Instruct 8B
173 tok/s+0%
GPT-5.4 mini (medium)
175 tok/s+1%
OpenAI: GPT-5 Codex
177 tok/s+2%

Benchmarks

MMLU-Pro
77.7%
GPQA Diamond
65.9%
HLE
6.8%
LiveCodeBench
51.5%
SciCode
30.4%
TerminalBench Hard
6.1%
MATH-500
97.5%
AIME
72.7%
AIME 2025
66.3%
IFBench
33.1%
Long Context Recall
22.7%
Tau2
10.2%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)

NVIDIA

Q: 9.1$0.90/1M
Slower: 70%Pricier: 323%

Mistral Large 2 (Nov '24)

Mistral

Q: 9.1$3.00/1M
Slower: 70%Pricier: 1308%

Mistral Small 3.2

Mistral

Q: 9.1$0.13/1M
Cheaper: 40%

GLM-4.5V (Reasoning)

Z AI

Q: 9.1$0.90/1M
Slower: 71%Pricier: 323%

ERNIE 4.5 300B A47B

Baidu

Q: 9.0$0.48/1M131K ctx
Slower: 86%Pricier: 128%

Ministral 3 8B

Mistral

Q: 9.0$0.15/1M
Slower: 43%Cheaper: 30%
Compare all 7 models