wenxinChat
Baidu: ERNIE 4.5 21B A3B
baidu/ernie-4.5-21b-a3b
120KContext Window
8KMax Output
Supported Protocols:max_tokenstemperaturetop_pstopfrequency_penaltypresence_penaltyseedtop_krepetition_penaltytoolstool_choice
Online
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.
Capabilities
🧠 Reasoning🔧 Function CallingText GenerationCode GenerationAnalysis & Reasoningmodels.reasoning
Technical Specs
Input Modality
Text
Output Modality
Text
Arch
—
Default Temperature
0.8
Default Top_P
0.8
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-4.5-21b-a3b",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)FAQ
Baidu: ERNIE 4.5 21B A3B
baidu/ernie-4.5-21b-a3b
In< ¥0.001/1K
Out< ¥0.001/1K
Context Window120K
Max Output8K
Related Models
View All → →Ready to get started?
Get 1M free tokens on registration, no monthly fees or minimum spend
Register Now →