AI Models/wenxin/Baidu: ERNIE 4.5 21B A3B
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 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-4.5-21b-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 →