Was diese Seite klärt
A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with
- Baidu Wenxin · baidu/ernie-4.5-vl-28b-a3b
- text+image->text · China-Modellroute
- 30.000 context · 0,14 $ input