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
46th of 444
Top 10%
Coding Index
30.5
77th of 354
Top 22%
Price/1M
$2.40
552nd cheapest
700% above median
Top 81%
Speed
35 tok/s
Top 55%
TTFT
1.64s
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 $0.30/1M tokens.
Daily
$2.40
Monthly
$72.00
35
tokens/sec
Faster than 45% of models
1.64
seconds
Faster than 17% of models
59.59
seconds
Faster than 3% of models
Market Median
45 tok/s
24% slower
Median TTFT
0.42s
292% 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