Loading...
Loading...
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design with early fusion of multimodal tokens, allowing the model to process and reason across text and images within the same context.
Quality Index
32.4
88th of 444
Top 20%
Coding Index
25.3
108th of 354
Top 31%
Price/1M
$0.11
241st cheapest
62% below median
Top 35%
Speed
51 tok/s
Top 47%
TTFT
0.34s
Context Window
256K
91st largest
Top 29%
Input
$0.10
per 1M tokens
Output
$0.15
per 1M tokens
Blended
$0.11
per 1M tokens
Cheaper than 65% of models. Median price is $0.30/1M tokens.
Daily
$0.11
Monthly
$3.39
51
tokens/sec
Faster than 53% of models
0.34
seconds
Faster than 56% of models
39.58
seconds
Faster than 6% of models
Market Median
45 tok/s
12% faster
Median TTFT
0.42s
20% faster
Throughput/Dollar
451
tok/s per $/1M
Speed Comparison
Context Window
256K
tokens
Larger than 71% of models
Max Output
66K
tokens
26% of context
3.6M
1.0K
16-24 GB
RTX 4090 / M2 Max