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 feesInput 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
Baidu: ERNIE 4.5 VL 28B A3B
baidu/ernie-4.5-vl-28b-a3b
In< ¥0.001/1K
Out< ¥0.001/1K
Context Window30K
Max Output8K
Related Models
View All → →Ready to get started?
Get 1M free tokens on registration, no monthly fees or minimum spend
Register Now →