About
QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks,...
Related Models
Pricing
Input
$0.66
per 1M tokens
Output
$1.00
per 1M tokens
Blended
$0.74
per 1M tokens
Cheaper than 45% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.74
Monthly
$22.35
vs. Similar Models
Qwen3 235B A22B (Reasoning)Q:0.0
$2.63+252%
Qwen3 VL 30B A3B (Reasoning)Q:-0.1
$0.34-55%
Qwen: Qwen3 Coder 30B A3B InstructQ:+0.2
$0.12-84%
Gemma 4 12B (Non-reasoning)Q:-0.2
$0.15-80%
Performance
32
tokens/sec
Faster than 2% of models
0.47
seconds
Faster than 90% of models
77.77
seconds
Faster than 2% of models
Market Median
94 tok/s
66% slower
Median TTFT
1.11s
58% faster
Throughput/Dollar
43
tok/s per $/1M
Speed Comparison
Qwen3.5 0.8B (Non-reasoning)
30 tok/s-6%
OpenAI: o3 Pro
34 tok/s+6%
Gemma 3 4B Instruct
34 tok/s+6%
Context Window
131K
tokens
Larger than 27% of models
Max Output
131K
tokens
100% of context
Benchmarks
MMLU-Pro
76.4%
GPQA Diamond
59.3%
HLE
8.2%
LiveCodeBench
63.1%
SciCode
35.8%
TerminalBench HardNot evaluated
MATH-500
95.7%
AIME
78.0%
AIME 2025
29.0%
IFBench
38.8%
Long Context Recall
25.0%
Tau2Not evaluated
Market AverageTop Score