ModelWatch

Compare models

Up to 4 models side by side.

Provider
Alibaba (Qwen)
Listed
Date added to OpenRouter
Aug 12, 2026
Input price
USD per 1M tokens
$2
Output price
USD per 1M tokens
$6
Workload cost
Chat reply (2K in, 500 out)
$0.0070
Context window
1.05M
Max output
131K
Output speed
tokens per second
42
Time to first token
seconds
5.07s
Intelligence Index
Artificial Analysis Intelligence Index: a composite of reasoning, knowledge, math and coding evaluations.
n/a
Engineering Index
Artificial Analysis Engineering Index: engineering and technical problem solving.
n/a
Inputs
text
Open weights
Yes
Good at
long-contextopen-weights
Notes
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is...

Best value in each row is highlighted. Share this page's URL to share the comparison.