Using OpenAI Client with DashScope API - Qwen3-VL

Powered by Mintlify

Auto-generate your docs

You can use Qwen3-VL models through the DashScope API using the OpenAI client library. This provides a familiar interface for interacting with the models.

Basic Setup

First, install the OpenAI Python client:

pip install openai

Image Understanding Example

Here’s how to use the DashScope API with an OpenAI-compatible client:

from openai import OpenAI

# Set your DASHSCOPE_API_KEY here
DASHSCOPE_API_KEY = "your-api-key-here"

client = OpenAI(
    api_key=DASHSCOPE_API_KEY,
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-vl-235b-a22b-instruct",
    messages=[{"role": "user", "content": [
        {"type": "image_url",
         "image_url": {"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"}},
        {"type": "text", "text": "这是什么"},
    ]}]
)
print(completion.model_dump_json())

Key Features

OpenAI-Compatible API: Use familiar OpenAI client patterns
Multi-Modal Support: Send images via URLs with image_url type
Model Selection: Choose from available Qwen3-VL model sizes
Flexible Content: Combine text and images in a single request

API Configuration

Base URL: https://dashscope.aliyuncs.com/compatible-mode/v1
Authentication: Use your DashScope API key
Available Models: qwen3-vl-235b-a22b-instruct and other Qwen3-VL variants

Additional Resources

For more detailed usage and advanced features, refer to the Aliyun DashScope documentation.