Skip to main content
Back to Explore

Qwen3 235B A22B 2507 Instruct

Alibaba·Released 2025-07-21
Open SourceMoE
Compare

Related Models

Qwen: Qwen3.7 Plus2026-06-03Qwen: Qwen3.7 Max2026-05-21Qwen: Qwen3.6 27B2026-04-27Qwen: Qwen3.6 35B A3B2026-04-27Qwen: Qwen3.5 Plus 2026-04-202026-04-27Qwen: Qwen3.6 Flash2026-04-27Qwen: Qwen3.6 Max Preview2026-04-27Qwen3.6 27B (Non-reasoning)2026-04-22

Pricing

Input

$0.20

per 1M tokens

Output

$0.82

per 1M tokens

Blended

$0.36

per 1M tokens

Cheaper than 58% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.36

Monthly

$10.68

vs. Similar Models

Nova 2.0 Lite (high)Q:0.0
$0.85+139%
Seed-OSS-36B-InstructQ:+0.1
$0.30-16%
Grok 3Q:+0.2
$8.00+2147%
OpenAI: o3 Mini HighQ:+0.2
$1.93+441%

Performance

64

tokens/sec

Faster than 32% of models

1.27

seconds

Faster than 41% of models

1.27

seconds

Faster than 61% of models

Market Median

95 tok/s

33% slower

Median TTFT

1.11s

15% slower

Throughput/Dollar

179

tok/s per $/1M

Speed Comparison

Gemma 3n E2B Instruct
64 tok/s+1%
Apertus 70B Instruct
64 tok/s+1%
Cohere: Command A
65 tok/s+1%

Benchmarks

MMLU-Pro
82.8%
GPQA Diamond
75.3%
HLE
10.6%
LiveCodeBench
52.4%
SciCode
36.0%
TerminalBench Hard
15.2%
MATH-500
98.0%
AIME
71.7%
AIME 2025
71.7%
IFBench
46.1%
Long Context Recall
31.2%
Tau2
33.3%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Nova 2.0 Lite (high)

Amazon

Q: 18.2$0.85/1M
Faster: 182%Pricier: 139%

Seed-OSS-36B-Instruct

ByteDance

Q: 18.3$0.30/1M
Slower: 39%Cheaper: 16%

Grok 3

xAI

Q: 18.4$8.00/1M131K ctx
Slower: 41%Pricier: 2147%

OpenAI: o3 Mini High

OpenAI

Q: 18.4$1.93/1M200K ctx
Faster: 250%Pricier: 441%

Qwen3 Coder 480B A35B Instruct

Alibaba

Q: 18.0$0.68/1M
Pricier: 90%

Magistral Medium 1.2

Mistral

Q: 17.9$2.75/1M
Slower: 41%Pricier: 672%
Compare all 7 models