Qwen-Omni

# Prerequisites:
# pip install openai

import os
from openai import OpenAI

# Initialize the client
client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope.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}")

// Prerequisites:
// npm install openai

import OpenAI from "openai";

// Initialize the client
const openai = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
});

// Send request (with web search enabled)
const completion = await openai.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
    }
});

console.log("Model response (with real-time information):");

for await (const chunk of completion) {
    if (Array.isArray(chunk.choices) && chunk.choices.length > 0) {
        if (chunk.choices[0].delta.content) {
            process.stdout.write(chunk.choices[0].delta.content);
        }
    }
}
console.log();

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "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_search": true
}'

import os
from openai import OpenAI

client = OpenAI(
    # If no environment variable is set, replace the next line with your Model Studio API key: api_key="sk-xxx"
    # 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 base URL is for the China (Beijing) region. URLs vary by region.
    base_url="https://dashscope.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 OpenAI from "openai";

const openai = new OpenAI({
     // If no environment variable is set, replace the next line with your Model Studio API key: apiKey:"sk-xxx"
    // 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
    apiKey: process.env.DASHSCOPE_API_KEY, 
    // The following base URL is for the China (Beijing) region. URLs vary by region.
    baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
});

const completion = await openai.chat.completions.create({
    model: "qwen3-omni-flash",
    messages: [
        { role: "user", content: "Who are you?" }
    ],
    // stream must be set to True, otherwise an error occurs.
    stream: true,
    stream_options: {
        include_usage: true
    },
    // 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" }
});

for await (const chunk of completion) {
    if (Array.isArray(chunk.choices) && chunk.choices.length > 0) {
        console.log(chunk.choices[0].delta);
    } else {
        console.log(chunk.usage);
    }
}

# ======= Important note =======
# 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
# The following base URL is for the China (Beijing) region. URLs vary by region./chat/completions
# === Delete this comment before execution ===

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3-omni-flash",
    "messages": [
        {
            "role": "user",
            "content": "Who are you?"
        }
    ],
    "stream":true,
    "stream_options":{
        "include_usage":true
    },
    "modalities":["text"],
    "enable_thinking": true
}'

import os
from openai import OpenAI

# Initialize the OpenAI client
client = OpenAI(
    # If no environment variable is set, replace the next line with your Model Studio API key: api_key="sk-xxx"
    # 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 base URL is for the China (Beijing) region. URLs vary by region.
    base_url="https://dashscope.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 OpenAI from "openai";

const openai = new OpenAI({
     // If no environment variable is set, replace the next line with your Model Studio API key: apiKey: "sk-xxx"
    // 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
    apiKey: process.env.DASHSCOPE_API_KEY, 
    // The following base URL is for the China (Beijing) region. URLs vary by region.
    baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
});

const completion = await openai.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." }]
        }],
    stream: true,
    stream_options: {
        include_usage: true
    },
    modalities: ["text"]
});


for await (const chunk of completion) {
    if (Array.isArray(chunk.choices) && chunk.choices.length > 0) {
        console.log(chunk.choices[0].delta);
    } else {
        console.log(chunk.usage);
    }
}

# ======= Important note =======
# 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
# The following base URL is for the China (Beijing) region. URLs vary by region./chat/completions
# === Delete this comment before execution ===

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "qwen3.5-omni-plus",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_audio",
          "input_audio": {
            "data": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.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."
        }
      ]
    }
  ],
  "stream": true,
  "stream_options": {
    "include_usage": true
  },
  "modalities": ["text"]
}'

import os
from openai import OpenAI
import base64

client = OpenAI(
    # If no environment variable is set, replace the next line with your Model Studio API key: api_key="sk-xxx"
    # 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 base URL is for the China (Beijing) region. URLs vary by region.
    base_url="https://dashscope.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)

import OpenAI from "openai";
import { readFileSync } from 'fs';

const openai = new OpenAI({
     // If no environment variable is set, replace the next line with your Model Studio API key: apiKey: "sk-xxx"
    // 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
    apiKey: process.env.DASHSCOPE_API_KEY, 
    // The following base URL is for the China (Beijing) region. URLs vary by region.
    baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
});

const encodeImage = (imagePath) => {
    const imageFile = readFileSync(imagePath);
    return imageFile.toString('base64');
};
const base64Image = encodeImage("eagle.png")

const completion = await openai.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": `data:image/png;base64,${base64Image}` },
            },
            { "type": "text", "text": "What scene is depicted in the image?" }]
        }],
    stream: true,
    stream_options: {
        include_usage: true
    },
    modalities: ["text", "audio"],
    audio: { voice: "Tina", format: "wav" }
});

for await (const chunk of completion) {
    if (Array.isArray(chunk.choices) && chunk.choices.length > 0) {
        console.log(chunk.choices[0].delta);
    } else {
        console.log(chunk.usage);
    }
}

import os
from openai import OpenAI
import base64
import numpy as np
import soundfile as sf
import requests

client = OpenAI(
    # If no environment variable is set, replace the next line with your Model Studio API key: api_key="sk-xxx"
    # 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 base URL is for the China (Beijing) region. URLs vary by region.
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)


def encode_audio(audio_path):
    with open(audio_path, "rb") as audio_file:
        return base64.b64encode(audio_file.read()).decode("utf-8")


base64_audio = encode_audio("welcome.mp3")

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": f"data:;base64,{base64_audio}",
                        "format": "mp3",
                    },
                },
                {"type": "text", "text": "What is this audio about"},
            ],
        },
    ],
    # 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)

import OpenAI from "openai";
import { readFileSync } from 'fs';

const openai = new OpenAI({
     // If no environment variable is set, replace the next line with your Model Studio API key: apiKey: "sk-xxx"
    // 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
    apiKey: process.env.DASHSCOPE_API_KEY, 
    // The following base URL is for the China (Beijing) region. URLs vary by region.
    baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
});

const encodeAudio = (audioPath) => {
    const audioFile = readFileSync(audioPath);
    return audioFile.toString('base64');
};
const base64Audio = encodeAudio("welcome.mp3")

const completion = await openai.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": `data:;base64,${base64Audio}`, "format": "mp3" },
            },
            { "type": "text", "text": "What is this audio about" }]
        }],
    stream: true,
    stream_options: {
        include_usage: true
    },
    modalities: ["text", "audio"],
    audio: { voice: "Tina", format: "wav" }
});

for await (const chunk of completion) {
    if (Array.isArray(chunk.choices) && chunk.choices.length > 0) {
        console.log(chunk.choices[0].delta);
    } else {
        console.log(chunk.usage);
    }
}