Baidu: ERNIE 4.5 VL 424B A47B
7.0 / 10
123K context
Proprietary
About this model
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...
Benchmark Scores
MMMU
70.0
Technical Specs
- Architecture: text+image->text
- Context Window: 123,000 tokens
- Input Modalities: text
Hardware Requirements
- API-only (no local hardware needed)
Pricing
| Input | Output | Currency |
|---|---|---|
| 0.42 / 1M tokens | 1.25 / 1M tokens | USD |