Loading...
Loading...
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
Input
$0.14
per 1M tokens
Output
$1.00
per 1M tokens
Blended
$0.35
per 1M tokens
Cheaper than 59% of models. Median price is $0.56/1M tokens.
Daily
$0.35
Monthly
$10.65
126
tokens/sec
Faster than 69% of models
1.17
seconds
Faster than 44% of models
16.99
seconds
Faster than 29% of models
Market Median
86 tok/s
47% faster
Median TTFT
1.07s
9% slower
Throughput/Dollar
356
tok/s per $/1M
Speed Comparison
Context Window
262K
tokens
Larger than 66% of models
Max Output
82K
tokens
31% of context
3.4M
1.4K
48-80 GB
A100 80GB
Quality Index
37.1
95th of 507
Top 19%
Coding Index
30.3
117th of 417
Top 28%
Price/1M
$0.35
260th cheapest
37% below median
Top 41%
Speed
126 tok/s
Top 31%
TTFT
1.17s
Context Window
262K
91st largest
Top 34%