DataLearner logo
ER

ERNIE-4.5-VL-28B-Base-A3B

Multimodal modelERNIE-4.5

ERNIE-4.5-VL-28B-Base-A3B

Release date: 2025-06-28Updated: 2025-06-28Views: 665
Live demoGitHubHugging FaceCompare
Parameters
28B
Context length
128K
Multilingual
Supported
Reasoning ability
3/5

ERNIE-4.5-VL-28B-Base-A3B is an AI model published by Baidu, released on 2025-06-28, for Multimodal model, with 28B parameters, and 128K context length, requiring about 56GB storage.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

ERNIE-4.5-VL-28B-Base-A3B

Model basics

Reasoning traces
No data
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
64K tokens
Model type
Multimodal model
Modality (in / out)
Text, Image → Text
Release date
2025-06-28
Model file size
56GB
MoE architecture
Yes
Total params / Active params
28B / 3B
Knowledge cutoff
No data
ERNIE-4.5-VL-28B-Base-A3B

Open source & experience

Code license
Weights license
MIT License- Commercial use permitted
GitHub repo
N/A
Live demo
N/A
ERNIE-4.5-VL-28B-Base-A3B

Official resources

Paper
N/A
DataLearnerAI blog
N/A
ERNIE-4.5-VL-28B-Base-A3B

API details

API speed
4/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$2.50/ 1M tokens$80.00/ 1M tokens
Image-$2.50/ 1M tokens

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

ERNIE-4.5-VL-28B-Base-A3B

Publisher

ERNIE-4.5-VL-28B-Base-A3B

Model Overview

ERNIE-4.5-VL-28B-Base-A3B is an AI model published by Baidu, released on 2025-06-28, for Multimodal model, with 28B parameters, and 128K context length, requiring about 56GB storage.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code