ERNIE 4.5 VL 424B A47B
424Bby Baidu
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 using a heterogeneous MoE architecture and modality-isolated routing to enable high-fidelity cross-modal reasoning, image understanding, and long-context generation (up to 131k tokens). Fine-tuned with techniques like SFT, DPO, UPO, and RLVR, this model supports both “thinking” and non-thinking inference modes. Designed for vision-language tasks in English and Chinese, it is optimized for efficient scaling and can operate under 4-bit/8-bit quantization.
Specifications
Technical details and pricing.
Benchmarks
12 benchmark scores from Artificial Analysis.
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Frequently Asked Questions
What is ERNIE 4.5 VL 424B A47B good for?
Use ERNIE 4.5 VL 424B A47B for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.
How much does ERNIE 4.5 VL 424B A47B cost?
Pricing is based on usage. Current rates are $0.28/1M tokens for input and $1.10/1M tokens for output.
Can I try ERNIE 4.5 VL 424B A47B for free?
Yes. You can start a chat instantly and test the model before deciding on a plan.
Does ERNIE 4.5 VL 424B A47B support images or audio?
ERNIE 4.5 VL 424B A47B can understand images.
Similar Models
Other models you might want to explore.
Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.