ERNIE 4.5 VL 28B A3B

About ERNIE 4.5 VL 28B A3B

A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated routing. Built with scaling-efficient infrastructure for high-throughput training and inference, the model leverages advanced post-training techniques including SFT, DPO, and UPO for optimized performance, while supporting an impressive 131K context length and RLVR alignment for superior cross-modal reasoning and generation capabilities.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Baidu Model Lineup

Compare all models from Baidu to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Llama 3 70B Instruct

Meta

Input: $0.30

Output: $0.40

Context: 8k

Ling-2.6-1T

Inclusionai

Input: $0.07

Output: $0.63

Context: 262k

Grok 4.1 Fast

xAI

Input: $0.20

Output: $0.50

Context: 2.0M

Grok 4 Fast

xAI

Input: $0.20

Output: $0.50

Context: 2.0M

💡 Cheaper Alternatives

Same Brand (Baidu)

Cross Brand

🚀 Quick Start

Get started with ERNIE 4.5 VL 28B A3B API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="baidu/ernie-4.5-vl-28b-a3b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision