AI Models/wenxin/Baidu: ERNIE 4.5 VL 28B A3B
wenxinChat

Baidu: ERNIE 4.5 VL 28B A3B

baidu/ernie-4.5-vl-28b-a3b
30KContext Window
8KMax Output
Supported Protocols:reasoninginclude_reasoningmax_tokenstemperaturetop_pstopfrequency_penaltypresence_penaltyseedtop_krepetition_penaltytoolstool_choice
Online

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.

Capabilities

👁 Vision🧠 Reasoning🔧 Function CallingText GenerationCode GenerationAnalysis & Reasoningmodels.reasoning

Technical Specs

Input Modality
Text、Image
Output Modality
Text
Arch

Pricing

Pay per use, no monthly fees
Input Token< ¥0.001/1K Token
Output Token< ¥0.001/1K Token

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_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)

FAQ

Ready to get started?

Get 1M free tokens on registration, no monthly fees or minimum spend

Register Now →