Loading...
Loading...
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
Input
$0.13
per 1M tokens
Output
$0.52
per 1M tokens
Blended
$0.23
per 1M tokens
Cheaper than 68% of models. Median price is $0.56/1M tokens.
Daily
$0.23
Monthly
$6.83
124
tokens/sec
Faster than 68% of models
1.02
seconds
Faster than 53% of models
1.02
seconds
Faster than 67% of models
Market Median
86 tok/s
45% faster
Median TTFT
1.07s
5% faster
Throughput/Dollar
547
tok/s per $/1M
Speed Comparison
Context Window
131K
tokens
Larger than 33% of models
Max Output
33K
tokens
25% of context
915.4K
568
24-48 GB
A6000 / M3 Ultra
Quality Index
16.1
300th of 507
Top 59%
Coding Index
14.3
258th of 417
Top 62%
Math Index
72.3
90th of 269
Top 34%
Price/1M
$0.23
201st cheapest
59% below median
Top 32%
Speed
124 tok/s
Top 32%
TTFT
1.02s
Context Window
131K
201st largest
Top 67%