Loading...
Loading...
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
Input
$0.39
per 1M tokens
Output
$2.34
per 1M tokens
Blended
$0.88
per 1M tokens
Cheaper than 38% of models. Median price is $0.56/1M tokens.
Daily
$0.88
Monthly
$26.32
52
tokens/sec
Faster than 23% of models
1.52
seconds
Faster than 30% of models
62.89
seconds
Faster than 4% of models
Market Median
86 tok/s
40% slower
Median TTFT
1.07s
42% slower
Throughput/Dollar
59
tok/s per $/1M
Speed Comparison
Context Window
262K
tokens
Larger than 66% of models
Max Output
66K
tokens
25% of context
645.8K
1.5K
Multi-GPU
8x A100 / H100
Quality Index
45.0
41st of 507
Top 8%
Coding Index
41.3
42nd of 417
Top 10%
Price/1M
$0.88
393rd cheapest
57% above median
Top 62%
Speed
52 tok/s
Top 77%
TTFT
1.52s
Context Window
262K
91st largest
Top 34%