Loading...
Loading...
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it delivers major gains in factual accuracy, complex reasoning, instruction following, alignment with human preferences, and agentic behavior.
Quality Index
39.9
45th of 442
Top 10%
Coding Index
30.5
76th of 352
Top 22%
Price/1M
$2.40
548th cheapest
674% above median
Top 81%
Speed
34 tok/s
Top 58%
TTFT
1.77s
Context Window
262K
61st largest
Top 25%
Input
$1.20
per 1M tokens
Output
$6.00
per 1M tokens
Blended
$2.40
per 1M tokens
Cheaper than 19% of models. Median price is $0.31/1M tokens.
Daily
$2.40
Monthly
$72.00
34
tokens/sec
Faster than 42% of models
1.77
seconds
Faster than 14% of models
60.43
seconds
Faster than 2% of models
Market Median
46 tok/s
25% slower
Median TTFT
0.42s
324% slower
Throughput/Dollar
14
tok/s per $/1M
Speed Comparison
Context Window
262K
tokens
Larger than 75% of models
Max Output
33K
tokens
13% of context