About
Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...
Related Models
Pricing
Input
$0.33
per 1M tokens
Output
$1.95
per 1M tokens
Blended
$0.73
per 1M tokens
Cheaper than 48% of models. Median price is $0.67/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.73
Monthly
$21.94
vs. Similar Models
Gemini 3 Pro Preview (high)Q:0.0
$4.50+515%
Z.ai: GLM 5Q:-0.1
$0.93+27%
Grok Build 0.1 0616Q:+0.2
$1.25+71%
OpenAI: GPT-5.4 MiniQ:+0.4
$1.69+131%
Performance
53
tokens/sec
Faster than 20% of models
1.80
seconds
Faster than 29% of models
107.41
seconds
Faster than 1% of models
Market Median
93 tok/s
44% slower
Median TTFT
1.13s
60% slower
Throughput/Dollar
72
tok/s per $/1M
Speed Comparison
Qwen: Qwen3 VL 235B A22B Instruct
53 tok/s+0%
Llama 3.2 Instruct 3B
53 tok/s+0%
Z.ai: GLM 4.5V
52 tok/s-0%
Context Window
1.0M
tokens
Larger than 80% of models
Max Output
66K
tokens
7% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
88.2%
HLE
25.7%
LiveCodeBenchNot evaluated
SciCode
40.7%
TerminalBench Hard
43.9%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
75.2%
Long Context Recall
69.7%
Tau2
97.7%
Market AverageTop Score