Qwen-Omni

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3.5-omni-plus",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
                    },
                },
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250211/tixcef/cherry.wav",
                        "format": "wav"
                    },
                },
                {"type": "text", "text": "Describe the image content and tell me what the audio is about."},
            ],
        },
    ],
    modalities=["text", "audio"],
    audio={"voice": "Tina", "format": "wav"},
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in completion:
    if chunk.choices:
        print(chunk.choices[0].delta)
    else:
        print(chunk.usage)

# Prerequisites:
# pip install openai

import os
from openai import OpenAI

# Initialize the client
client = OpenAI(
    # API Keys differ between Singapore and Beijing regions. Get API Key:https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following URL is for the Singapore region. When calling, replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

# Send request (with web search enabled)
try:
    completion = client.chat.completions.create(
        model="qwen3.5-omni-plus",
        messages=[{
            "role": "user",
            "content": "What is today's date and day of the week, and what important holidays are there today?"
        }],
        stream=True,
        stream_options={"include_usage": True},
        # Enable web search
        extra_body={
            "enable_search": True
        }
    )

    print("Model response (with real-time information):")
    for chunk in completion:
        if chunk.choices and chunk.choices[0].delta.content:
            print(chunk.choices[0].delta.content, end="")
    print()

except Exception as e:
    print(f"Request failed:{e}")

import os
from openai import OpenAI

client = OpenAI(
    # API keys for the Singapore and Beijing regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following URL is for the Singapore region. When calling, replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-omni-flash",
    messages=[{"role": "user", "content": "Who are you?"}],

    # Enable or disable thinking mode. Audio output is not supported in thinking mode. Qwen-Omni-Turbo does not support enable_thinking.
    extra_body={'enable_thinking': True},

    # Set the output modality. Two options are supported in non-thinking mode: ["text","audio"] and ["text"]. Only ["text"] is supported in thinking mode.
    modalities=["text"],

    # Set the voice. The audio parameter is not supported in thinking mode.
    # audio={"voice": "Tina", "format": "wav"},
    # stream must be set to True, otherwise an error occurs.
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in completion:
    if chunk.choices:
        print(chunk.choices[0].delta)
    else:
        print(chunk.usage)

import os
from openai import OpenAI

client = OpenAI(
    # API keys for the Singapore and Beijing regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following URL is for the Singapore region. When calling, replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3.5-omni-plus", # For Qwen3-Omni-Flash, run in non-thinking mode.
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3",
                        "format": "mp3",
                    },
                },
                {"type": "text", "text": "What is this audio about"},
            ],
        },
        {
            "role": "assistant",
            "content": [{"type": "text", "text": "This audio says: Welcome to Alibaba Cloud"}],
        },
        {
            "role": "user",
            "content": [{"type": "text", "text": "Tell me about this company."}],
        },
    ],
    # Set the output modality. Two options are currently supported: ["text","audio"] and ["text"]
    modalities=["text"],
    # stream must be set to True, otherwise an error occurs.
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in completion:
    if chunk.choices:
        print(chunk.choices[0].delta)
    else:
        print(chunk.usage)

import os
from openai import OpenAI
import base64

client = OpenAI(
    # API keys for the Singapore and Beijing regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following URL is for the Singapore region. When calling, replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

# Base64 encoding format
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")

base64_image = encode_image("eagle.png")

completion = client.chat.completions.create(
    model="qwen3.5-omni-plus", # For Qwen3-Omni-Flash, run in non-thinking mode.
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{base64_image}"},
                },
                {"type": "text", "text": "What scene is depicted in the image?"},
            ],
        },
    ],
    # Set the output modality. Two options are currently supported: ["text","audio"] and ["text"]
    modalities=["text", "audio"],
    audio={"voice": "Tina", "format": "wav"},
    # stream must be set to True, otherwise an error occurs.
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in completion:
    if chunk.choices:
        print(chunk.choices[0].delta)
    else:
        print(chunk.usage)