ERNIE-4.5-VL-424B-A47B-Base-PT
ERNIE-4.5-VL-424B-A47B-Base-PT is Baidu's multimodal mixture-of-experts base model with 424B total and 47B activated parameters per token, using a heterogeneous MoE structure with separate text and vision experts.
text + image → text · made by Baidu
$0.42→$1.25per Mtok in / out
Hugging Face Inference Providers
Sold by 1 way
| Seller | Lane | Rate |
|---|---|---|
| Hugging Face Inference Providers aggregator | novita | $0.42per Mtok in$1.25per Mtok outrouter.huggingface.co · read 2026-08-25 |
About
ERNIE-4.5-VL-424B-A47B-Base-PT — a text model from Baidu.
It takes text and images and returns text, with a context window of 131,072 tokens. The catalogue files it under chat.
Every current figure
- Maker
- Baidu
- Register
- model
- Takes
- text + image
- Returns
- text
- Context
- 131,072 tokens
- Parameters
- 424 billion · read from its own name, the total of a mixture
- Licence
- not read
Known as 1 name
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT