← All models
B

Baidu: ERNIE 4.5 VL 424B A47B

baidu/ernie-4.5-vl-424b-a47b

VisionReasoningStreaming

ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...

Pricing

Input

$0.42 / 1M

Output

$1.25 / 1M

Specs

Context

131,072 tokens

Input

image, text

Output

text

Knowledge cutoff: 2025-03-31

Released: 2025-06

Supported parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetop_ktop_p

Open weights · HuggingFace

127 downloads/mo
106 likes
apache-2.0 image-text-to-text
View on HuggingFace →