Baidu

ERNIE 4.5 21B A3B

A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneous MoE structures and modality-isolated routing. Supporting an extensive 131K token context length, the model achieves efficient inference via multi-expert parallel collaboration and quantization, while advanced post-training techniques including SFT, DPO, and UPO ensure optimized performance across diverse applications with specialized routing and balancing losses for superior task handling.

Input / 1M tokens

$0.070

Output / 1M tokens

$0.280

Context window

120K tokens

Provider

Baidu

Knowledge cutoff

2025-03-31