ERNIE 4.5 VL 424B | Baidu Multimodal MoE API

Name: Ernie 4.5 Vl 424b A47b API
Brand: baidu
Price: 0.42 USD
Availability: InStock

API 使用

使用以下代码示例接入我们的 API：

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="baidu/ernie-4.5-vl-424b-a47b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

模型介绍

Baidu ernie-4.5-vl-424b-a47b

ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active p

ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data using a heterogeneous MoE architecture and modality-isolated routing to enable high-fidelity cross-modal reasoning, image understanding, and long-context generation (up to 131k tokens). Fine-tuned with techniques like SFT, DPO, UPO, and RLVR, this model supports both “thinking” and non-thinking inference modes. Designed for vision-language tasks in English and Chinese, it is optimized for efficient scaling and can operate under 4-bit/8-bit quantization.

Why It Looks Great

Large Language Model architecture for efficient processing
123000 context window for long document handling
Competitive pricing at $0.5/$1.4 per million tokens

Key Features

Context Window: 123000 tokens
Max Output: 16000 tokens
Vision: Supported
Function Calling: Supported

Specifications

Specification	Value
Provider	Baidu
Model Type	Large Language Model (LLM)
Architecture	N/A
Context Window	123000 tokens
Max Output	16000 tokens
Input	Text
Output	Text
Vision	Supported
Function Calling	Supported

Pricing

Token Type	Cost per Million Tokens
Input	$0.5
Output	$1.4

How to Use

Write your prompt — describe the task, provide context, and specify desired output format.
Submit — the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: baidu/ernie-4.5-vl-424b-a47b

API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="baidu/ernie-4.5-vl-424b-a47b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "baidu/ernie-4.5-vl-424b-a47b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

Model: baidu/ernie-4.5-vl-424b-a47b
Provider: Baidu

关于 Ernie 4.5 Vl 424b A47b 的常见问题

Ernie 4.5 Vl 424b A47b API 多少钱?+

WaveSpeedAI 定价:输入每百万 token $0.42,输出每百万 token $1.25。Prompt 缓存和批处理单独计费,可显著降低长上下文、高重复任务的实际成本。

Ernie 4.5 Vl 424b A47b 的上下文窗口是多大?+

Ernie 4.5 Vl 424b A47b 单次请求最多支持 123K 上下文 token,输出最多 16K token。

Ernie 4.5 Vl 424b A47b 是否兼容 OpenAI?+

是的。WaveSpeedAI 通过 https://llm.wavespeed.ai/v1 的 OpenAI 兼容端点提供 Ernie 4.5 Vl 424b A47b。把官方 OpenAI SDK 的 base URL 指向该地址,使用 WaveSpeedAI 的 API Key 即可,无需任何其他代码改动。

如何开始使用 Ernie 4.5 Vl 424b A47b?+

登录 WaveSpeedAI,在 Access Keys 中生成 API Key,使用上方显示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 发送请求。新账户可获得免费额度,用于试用 Ernie 4.5 Vl 424b A47b。

定价

试用模型