Alibaba Cloud Model Studio:Visual understanding (Qwen-VL)

Python

from openai import OpenAI
import os

client = OpenAI(
    # The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see 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 Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
)

completion = client.chat.completions.create(
    model="qwen3-vl-plus",  # This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/model-studio/getting-started/models
    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": "text", "text": "What is depicted in the image?"},
            ],
        },
    ],
)
print(completion.choices[0].message.content)

Response

This is a photo taken on a beach. In the photo, a person and a dog are sitting on the sand with the sea and sky in the background. The person and the dog appear to be interacting, with the dog's front paw resting on the person's hand. Sunlight shines from the right side of the frame, adding a warm atmosphere to the scene.

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
  // The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
  // If you have not configured the environment variable, replace the following line with your Model Studio API key: apiKey: "sk-xxx"
  apiKey: process.env.DASHSCOPE_API_KEY,
  // The following base_url is for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
  baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
});

async function main() {
  const response = await openai.chat.completions.create({
    model: "qwen3-vl-plus",   // This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/model-studio/getting-started/models 
    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: "text",
            text: "What is depicted in the image?"
          }
        ]
      }
    ]
  });
  console.log(response.choices[0].message.content);
}
main()

This is a photo taken on a beach. In the photo, a person and a dog are sitting on the sand with the sea and sky in the background. The person and the dog appear to be interacting, with the dog's front paw resting on the person's hand. Sunlight shines from the right side of the frame, adding a warm atmosphere to the scene.

curl

# ======= Important =======
# The following base_url is for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# === Delete this comment before execution ===

curl --location 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
  "model": "qwen3-vl-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": "text", "text": "What is depicted in the image?"}
    ]
  }]
}'

Response

{
  "choices": [
    {
      "message": {
        "content": "This is a photo taken on a beach. In the photo, a person and a dog are sitting on the sand with the sea and sky in the background. The person and the dog appear to be interacting, with the dog's front paw resting on the person's hand. Sunlight shines from the right side of the frame, adding a warm atmosphere to the scene.",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 1270,
    "completion_tokens": 54,
    "total_tokens": 1324
  },
  "created": 1725948561,
  "system_fingerprint": null,
  "model": "qwen3-vl-plus",
  "id": "chatcmpl-0fd66f46-b09e-9164-a84f-3ebbbedbac15"
}

Python

import os
import dashscope

# The following base_url is for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

messages = [
{
    "role": "user",
    "content": [
    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
    {"text": "What is depicted in the image?"}]
}]

response = dashscope.MultiModalConversation.call(
    # The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured the environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen3-vl-plus',   # This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/model-studio/getting-started/models
    messages=messages
)

print(response.output.choices[0].message.content[0]["text"])

Response

This is a photo taken on a beach. In the photo, there is a woman and a dog. The woman is sitting on the sand, smiling and interacting with the dog. The dog is wearing a collar and appears to be shaking hands with the woman. The background is the sea and the sky, and the sunlight shining on them creates a warm atmosphere.

Java

import java.util.Arrays;
import java.util.Collections;

import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;

public class Main {
    
    // The following base_url is for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
    static {
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }
    
    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation(); 
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        Collections.singletonMap("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"),
                        Collections.singletonMap("text", "What is depicted in the image?"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If you have not configured the environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")  //  This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/model-studio/getting-started/models
                .messages(Arrays.asList(userMessage))
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }
    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

Response

This is a photo taken on a beach. In the photo, there is a person in a plaid shirt and a dog wearing a collar. The person and the dog are sitting face to face, seemingly interacting. The background is the sea and the sky, and the sunlight shining on them creates a warm atmosphere.

curl

# ======= Important =======
# The following base_url is for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen3-vl-plus",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
                    {"text": "What is depicted in the image?"}
                ]
            }
        ]
    }
}'

Response

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "This is a photo taken on a beach. In the photo, there is a person in a plaid shirt and a dog wearing a collar. They are sitting on the sand with the sea and sky in the background. Sunlight shines from the right side of the frame, adding a warm atmosphere to the scene."
            }
          ]
        }
      }
    ]
  },
  "usage": {
    "output_tokens": 55,
    "input_tokens": 1271,
    "image_tokens": 1247
  },
  "request_id": "ccf845a3-dc33-9cda-b581-20fe7dc23f70"
}

Python

import os
from openai import OpenAI

client = OpenAI(
    # The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see 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 Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-vl-plus",  #  This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/model-studio/getting-started/models
    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": "image_url","image_url": {"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},},
            {"type": "text", "text": "What do these images depict?"},
            ],
        }
    ],
)

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

Response

Image 1 shows a scene of a woman and a Labrador retriever interacting on a beach. The woman is wearing a plaid shirt and sitting on the sand, shaking hands with the dog. The background is the ocean waves and the sky, and the whole picture is filled with a warm and pleasant atmosphere.

Image 2 shows a scene of a tiger walking in a forest. The tiger's fur is orange with black stripes. It is stepping forward, surrounded by dense trees and vegetation. The ground is covered with fallen leaves, and the whole picture gives a feeling of wild nature.

Node.js

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
        // If you have not configured the environment variable, replace the following line with your Model Studio API key: apiKey: "sk-xxx"
        apiKey: process.env.DASHSCOPE_API_KEY,
        // The following base_url is for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
        baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    }
);

async function main() {
    const response = await openai.chat.completions.create({
        model: "qwen3-vl-plus",  // This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/models
        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: "image_url",image_url: {"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"}},
            {type: "text", text: "What do these images depict?" },
        ]}]
    });
    console.log(response.choices[0].message.content);
}

main()

Response

In the first image, a person and a dog are interacting on a beach. The person is wearing a plaid shirt, and the dog is wearing a collar. They seem to be shaking hands or giving a high-five.

In the second image, a tiger is walking in a forest. The tiger's fur is orange with black stripes, and the background is green trees and vegetation.

curl

# ======= Important =======
# The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following base_url is for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
  "model": "qwen3-vl-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": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"
          }
        },
        {
          "type": "text",
          "text": "What do these images depict?"
        }
      ]
    }
  ]
}'

Response

{
  "choices": [
    {
      "message": {
        "content": "Image 1 shows a scene of a woman and a Labrador retriever interacting on a beach. The woman is wearing a plaid shirt and sitting on the sand, shaking hands with the dog. The background is a sea view and a sunset sky, making the whole scene look very warm and harmonious.\n\nImage 2 shows a scene of a tiger walking in a forest. The tiger's fur is orange with black stripes. It is stepping forward, surrounded by dense trees and vegetation. The ground is covered with fallen leaves, and the whole picture is full of natural wildness and vitality.",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 2497,
    "completion_tokens": 109,
    "total_tokens": 2606
  },
  "created": 1725948561,
  "system_fingerprint": null,
  "model": "qwen3-vl-plus",
  "id": "chatcmpl-0fd66f46-b09e-9164-a84f-3ebbbedbac15"
}

Python

import os
import dashscope

# The following base_url is for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
            {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
            {"text": "What do these images depict?"}
        ]
    }
]

response = dashscope.MultiModalConversation.call(
    # The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured the environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen3-vl-plus', #  This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/model-studio/getting-started/models
    messages=messages
)

print(response.output.choices[0].message.content[0]["text"])

Response

These images show some animals and natural scenes. In the first image, a person and a dog are interacting on a beach. The second image is of a tiger walking in a forest.

Java

import java.util.Arrays;
import java.util.Collections;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;

public class Main {
    static {
        // The following base_url is for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }
    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        Collections.singletonMap("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"),
                        Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"),
                        Collections.singletonMap("text", "What do these images depict?"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")  //  This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/model-studio/getting-started/models
                .messages(Arrays.asList(userMessage))
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));    }
    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

Response

These images show some animals and natural scenes.

1. First image: A woman and a dog are interacting on a beach. The woman is wearing a plaid shirt and sitting on the sand, and the dog is wearing a collar and extending its paw to shake hands with the woman.
2. Second image: A tiger is walking in a forest. The tiger's fur is orange with black stripes, and the background is trees and leaves.

curl

# ======= Important =======
# The following base_url is for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# === Delete this comment before execution ===

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen3-vl-plus",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
                    {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
                    {"text": "What do these images show?"}
                ]
            }
        ]
    }
}'

Response

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "text": "These images show some animals and natural scenes. In the first image, a person and a dog are interacting on a beach. The second image is of a tiger walking in a forest."
            }
          ]
        }
      }
    ]
  },
  "usage": {
    "output_tokens": 81,
    "input_tokens": 1277,
    "image_tokens": 2497
  },
  "request_id": "ccf845a3-dc33-9cda-b581-20fe7dc23f70"
}

Python

import os
from openai import OpenAI

client = OpenAI(
    # API keys for the Singapore and China (Beijing) regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-an-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
    model="qwen3-vl-plus",
    messages=[
        {"role": "user","content": [{
            # When passing a video file directly, set the value of type to video_url.
            # When using the OpenAI SDK, one frame is extracted from the video every 0.5 seconds by default. This frequency cannot be changed. To customize the frame rate, use the DashScope SDK.
            "type": "video_url",            
            "video_url": {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241115/cqqkru/1.mp4"}},
            {"type": "text","text": "What is the content of this video?"}]
         }]
)
print(completion.choices[0].message.content)

Node.js

import OpenAI from "openai";

const openai = new OpenAI(
    {
        // API keys for the Singapore and China (Beijing) regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-an-api-key
        // If the environment variable is not configured, replace the following line with your Model Studio API key: apiKey: "sk-xxx"
        apiKey: process.env.DASHSCOPE_API_KEY,
        // The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
        baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    }
);

async function main() {
    const response = await openai.chat.completions.create({
        model: "qwen3-vl-plus",
        messages: [
        {role: "user",content: [
            // When passing a video file directly, set the value of type to video_url.
            // When using the OpenAI SDK, one frame is extracted from the video every 0.5 seconds by default. This frequency cannot be changed. To customize the frame rate, use the DashScope SDK.
            {type: "video_url", video_url: {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241115/cqqkru/1.mp4"}},
            {type: "text", text: "What is the content of this video?" },
        ]}]
    });
    console.log(response.choices[0].message.content);
}

main()

curl

# ======= Important Note =======
# This base_url is for the Singapore region. To use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1/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-vl-plus",
    "messages": [
    {"role": "user","content": [{"type": "video_url","video_url": {"url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241115/cqqkru/1.mp4"}},
    {"type": "text","text": "What is the content of this video?"}]}]
}'

Python

import dashscope
import os
# The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'
messages = [
    {"role": "user",
        "content": [
            # The fps parameter controls the video frame extraction frequency. It specifies that one frame is extracted every 1/fps seconds. For complete usage, see: https://www.alibabacloud.com/help/en/model-studio/use-qwen-by-calling-api?#2ed5ee7377fum
            {"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241115/cqqkru/1.mp4","fps":2},
            {"text": "What is the content of this video?"}
        ]
    }
]

response = dashscope.MultiModalConversation.call(
    # API keys for the Singapore and China (Beijing) regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-an-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key ="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen3-vl-plus',
    messages=messages
)

print(response.output.choices[0].message.content[0]["text"])

Java

import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;

import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;

public class Main {
   static {
            // The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
            Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
        }
    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        // The fps parameter controls the video frame extraction frequency. It specifies that one frame is extracted every 1/fps seconds. For complete usage, see: https://www.alibabacloud.com/help/en/model-studio/use-qwen-by-calling-api?#2ed5ee7377fum
        Map<String, Object> params = new HashMap<>();
        params.put("video", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241115/cqqkru/1.mp4");
        params.put("fps", 2);
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        params,
                        Collections.singletonMap("text", "What is the content of this video?"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // If you use a model in the China (Beijing) region, you must use an API key for the China (Beijing) region. Get an API key: https://bailian.console.alibabacloud.com/?tab=model#/api-key
                // If the environment variable is not configured, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")
                .messages(Arrays.asList(userMessage))
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }
    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl

# ======= Important =======
# The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# API keys for the Singapore and China (Beijing) regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-an-api-key
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen3-vl-plus",
    "input":{
        "messages":[
            {"role": "user","content": [{"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241115/cqqkru/1.mp4","fps":2},
            {"text": "What is the content of this video?"}]}]}
}'

Python

import os
from openai import OpenAI

client = OpenAI(
    # API keys for the Singapore and China (Beijing) regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-an-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
    model="qwen3-vl-plus", # This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see: https://www.alibabacloud.com/help/en/model-studio/models-and-pricing
    messages=[{"role": "user","content": [
        # When passing a list of images, the "type" parameter in the user message is "video".
        # When using the OpenAI SDK, the image list is assumed to be extracted from the video at a rate of one frame every 0.5 seconds. This cannot be changed. To customize the frame rate, use the DashScope SDK.
        {"type": "video","video": ["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"]},
        {"type": "text","text": "Describe the specific process in this video"},
    ]}]
)
print(completion.choices[0].message.content)

Node.js

// Make sure you have specified "type": "module" in your package.json file.
import OpenAI from "openai";

const openai = new OpenAI({
    // API keys for the Singapore and China (Beijing) regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-an-api-key
    // If the environment variable is not configured, replace the following line with your Model Studio API key: apiKey: "sk-xxx",
    apiKey: process.env.DASHSCOPE_API_KEY,
    // The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
    baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const response = await openai.chat.completions.create({
        model: "qwen3-vl-plus", // This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see: https://www.alibabacloud.com/help/en/model-studio/models-and-pricing
        messages: [{
            role: "user",
            content: [
                {
                    // When passing a list of images, the "type" parameter in the user message is "video".
                    // When using the OpenAI SDK, the image list is assumed to be extracted from the video at a rate of one frame every 0.5 seconds. This cannot be changed. To customize the frame rate, use the DashScope SDK.
                    type: "video",
                    video: [
                        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
                        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
                        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
                        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"
                    ]
                },
                {
                    type: "text",
                    text: "Describe the specific process in this video"
                }
            ]
        }]
    });
    console.log(response.choices[0].message.content);
}

main();

curl

# ======= Important =======
# API keys for the Singapore and China (Beijing) regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-an-api-key
# The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen3-vl-plus",
    "messages": [{"role": "user",
                "content": [{"type": "video",
                "video": ["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"]},
                {"type": "text",
                "text": "Describe the specific process in this video"}]}]
}'

Python

import os
import dashscope

# The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'
messages = [{"role": "user",
             "content": [
                  # If the model is from the Qwen2.5-VL or Qwen3-VL series and you pass a list of images, you can set the fps parameter. This indicates that the image list was extracted from the original video at a rate of one frame every 1/fps seconds.
                 {"video":["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
                           "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"],
                   "fps":2},
                 {"text": "Describe the specific process in this video"}]}]
response = dashscope.MultiModalConversation.call(
    # API keys for the Singapore and China (Beijing) regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-an-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model='qwen3-vl-plus',  # This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see: https://www.alibabacloud.com/help/en/model-studio/models-and-pricing
    messages=messages
)
print(response.output.choices[0].message.content[0]["text"])

Java

// DashScope SDK version 2.18.3 or later is required.
import java.util.Arrays;
import java.util.Collections;
import java.util.Map;

import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;

public class Main {
    static {
        // The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }
    private static final String MODEL_NAME = "qwen3-vl-plus";  // This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see: https://www.alibabacloud.com/help/en/model-studio/models-and-pricing
    public static void videoImageListSample() throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        // If the model is from the Qwen2.5-VL or Qwen3-VL series and you pass a list of images, you can set the fps parameter. This indicates that the image list was extracted from the original video at a rate of one frame every 1/fps seconds.
        Map<String, Object> params = Map.of(
                "video", Arrays.asList("https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
                        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
                        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
                        "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"),
                "fps",2);
        MultiModalMessage userMessage = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(
                        params,
                        Collections.singletonMap("text", "Describe the specific process in this video")))
                .build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // API keys for the Singapore and China (Beijing) regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-an-api-key
                // If the environment variable is not configured, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model(MODEL_NAME)
                .messages(Arrays.asList(userMessage)).build();
        MultiModalConversationResult result = conv.call(param);
        System.out.print(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }
    public static void main(String[] args) {
        try {
            videoImageListSample();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl

# ======= Important =======
# The following is the base_url for the Singapore region. If you use a model in the China (Beijing) region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# API keys for the Singapore and China (Beijing) regions are different. Get an API key: https://www.alibabacloud.com/help/en/model-studio/get-an-api-key
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
  "model": "qwen3-vl-plus",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "video": [
              "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
              "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
              "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
              "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"
            ],
            "fps":2
                 
          },
          {
            "text": "Describe the specific process in this video"
          }
        ]
      }
    ]
  }
}'

Python

import os
import dashscope

# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

# Replace xxx/eagle.png with the absolute path of your local image
local_path = "xxx/eagle.png"
image_path = f"file://{local_path}"
messages = [
                {'role':'user',
                'content': [{'image': image_path},
                            {'text': 'What is depicted in the image?'}]}]
response = dashscope.MultiModalConversation.call(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen3-vl-plus',  # This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models
    messages=messages)
print(response.output.choices[0].message.content[0]["text"])

Java

import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;

public class Main {

    static {
        // The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }
    
    public static void callWithLocalFile(String localPath)
            throws ApiException, NoApiKeyException, UploadFileException {
        String filePath = "file://"+localPath;
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(new HashMap<String, Object>(){{put("image", filePath);}},
                        new HashMap<String, Object>(){{put("text", "What is depicted in the image?");}})).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If the environment variable is not configured, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")  // This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models
                .messages(Arrays.asList(userMessage))
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));}

    public static void main(String[] args) {
        try {
            // Replace xxx/eagle.png with the absolute path of your local image
            callWithLocalFile("xxx/eagle.png");
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

OpenAI compatible

from openai import OpenAI
import os
import base64


# Encoding function: Converts a local file to a Base64-encoded string.
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")

# Replace xxx/eagle.png with the absolute path of your local image
base64_image = encode_image("xxx/eagle.png")
client = OpenAI(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    # The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
    model="qwen3-vl-plus", # This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    # When passing Base64 image data, note that the image format (image/{format}) must match the Content Type in the list of supported images. "f" is a string formatting method.
                    # PNG image:  f"data:image/png;base64,{base64_image}"
                    # JPEG image: f"data:image/jpeg;base64,{base64_image}"
                    # WEBP image: f"data:image/webp;base64,{base64_image}"
                    "image_url": {"url": f"data:image/png;base64,{base64_image}"},
                },
                {"type": "text", "text": "What is depicted in the image?"},
            ],
        }
    ],
)
print(completion.choices[0].message.content)

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


const openai = new OpenAI(
    {
        // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
        // If the environment variable is not configured, replace the following line with your Model Studio API key: apiKey: "sk-xxx"
        apiKey: process.env.DASHSCOPE_API_KEY,
        // The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
        baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    }
);

const encodeImage = (imagePath) => {
    const imageFile = readFileSync(imagePath);
    return imageFile.toString('base64');
  };
// Replace xxx/eagle.png with the absolute path of your local image
const base64Image = encodeImage("xxx/eagle.png")
async function main() {
    const completion = await openai.chat.completions.create({
        model: "qwen3-vl-plus",  // This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models
        messages: [
            {"role": "user",
            "content": [{"type": "image_url",
                            // Note: When passing Base64 data, the image format (image/{format}) must match the Content Type in the list of supported images.
                           // PNG image:  data:image/png;base64,${base64Image}
                          // JPEG image: data:image/jpeg;base64,${base64Image}
                         // WEBP image: data:image/webp;base64,${base64Image}
                        "image_url": {"url": `data:image/png;base64,${base64Image}`},},
                        {"type": "text", "text": "What is depicted in the image?"}]}]
    });
    console.log(completion.choices[0].message.content);
} 

main();

# ======= Important =======
# API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# === Delete this comment before execution ===

curl --location 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
  "model": "qwen3-vl-plus",
  "messages": [
  {
    "role": "user",
    "content": [
      {"type": "image_url", "image_url": {"url": "data:image/jpg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAA"}},
      {"type": "text", "text": "What is depicted in the image?"}
    ]
  }]
}'

DashScope

import base64
import os
import dashscope

# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

# Encoding function: Converts a local file to a Base64-encoded string.
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")


# Replace xxxx/eagle.png with the absolute path of your local image
base64_image = encode_image("xxxx/eagle.png")

messages = [
    {
        "role": "user",
        "content": [
            # Note: When passing Base64 data, the image format (image/{format}) must match the Content Type in the list of supported images. "f" is a string formatting method.
            # PNG image:  f"data:image/png;base64,{base64_image}"
            # JPEG image: f"data:image/jpeg;base64,{base64_image}"
            # WEBP image: f"data:image/webp;base64,{base64_image}"
            {"image": f"data:image/png;base64,{base64_image}"},
            {"text": "What is depicted in the image?"},
        ],
    },
]

response = dashscope.MultiModalConversation.call(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-vl-plus",  # This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models
    messages=messages,
)
print(response.output.choices[0].message.content[0]["text"])

import java.io.IOException;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.Base64;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;

import com.alibaba.dashscope.aigc.multimodalconversation.*;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;

public class Main {

    static {
        // The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }

    private static String encodeImageToBase64(String imagePath) throws IOException {
        Path path = Paths.get(imagePath);
        byte[] imageBytes = Files.readAllBytes(path);
        return Base64.getEncoder().encodeToString(imageBytes);
    }

    public static void callWithLocalFile(String localPath) throws ApiException, NoApiKeyException, UploadFileException, IOException {

        String base64Image = encodeImageToBase64(localPath); // Base64 encoding

        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        new HashMap<String, Object>() {{ put("image", "data:image/png;base64," + base64Image); }},
                        new HashMap<String, Object>() {{ put("text", "What is depicted in the image?"); }}
                )).build();

        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")
                .messages(Arrays.asList(userMessage))
                .build();

        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }

    public static void main(String[] args) {
        try {
            // Replace xxx/eagle.png with the absolute path of your local image
            callWithLocalFile("xxx/eagle.png");
        } catch (ApiException | NoApiKeyException | UploadFileException | IOException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

# ======= Important =======
# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# === Delete this comment before execution ===

curl -X POST https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen3-vl-plus",
    "input":{
        "messages":[
            {
             "role": "user",
             "content": [
               {"image": "data:image/png;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAA..."},
               {"text": "What is depicted in the image?"}
                ]
            }
        ]
    }
}'

Python

import os
import dashscope

# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

# Replace xxx/test.mp4 with the absolute path of your local video
local_path = "xxx/test.mp4"
video_path = f"file://{local_path}"
messages = [
                {'role':'user',
                # The fps parameter controls the number of frames extracted from the video. It means one frame is extracted every 1/fps seconds.
                'content': [{'video': video_path,"fps":2},
                            {'text': 'What does this video depict?'}]}]
response = MultiModalConversation.call(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen3-vl-plus',  
    messages=messages)
print(response.output.choices[0].message.content[0]["text"])

Java

import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;

public class Main {

    static {
        // The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }
    
    public static void callWithLocalFile(String localPath)
            throws ApiException, NoApiKeyException, UploadFileException {
        String filePath = "file://"+localPath;
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(new HashMap<String, Object>()
                                       {{
                                           put("video", filePath);// The fps parameter controls the number of frames extracted from the video. It means one frame is extracted every 1/fps seconds.
                                           put("fps", 2);
                                       }}, 
                        new HashMap<String, Object>(){{put("text", "What does this video depict?");}})).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If the environment variable is not configured, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")  
                .messages(Arrays.asList(userMessage))
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));}

    public static void main(String[] args) {
        try {
            // Replace xxx/test.mp4 with the absolute path of your local video
            callWithLocalFile("xxx/test.mp4");
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

OpenAI compatible

from openai import OpenAI
import os
import base64


# Encoding function: Converts a local file to a Base64-encoded string.
def encode_video(video_path):
    with open(video_path, "rb") as video_file:
        return base64.b64encode(video_file.read()).decode("utf-8")

# Replace xxx/test.mp4 with the absolute path of your local video
base64_video = encode_video("xxx/test.mp4")
client = OpenAI(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    # The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
    model="qwen3-vl-plus",  
    messages=[
        {
            "role": "user",
            "content": [
                {
                    # When passing a video file directly, set the value of type to video_url.
                    "type": "video_url",
                    "video_url": {"url": f"data:video/mp4;base64,{base64_video}"},
                },
                {"type": "text", "text": "What does this video depict?"},
            ],
        }
    ],
)
print(completion.choices[0].message.content)

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

const openai = new OpenAI(
    {
        // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
        // If the environment variable is not configured, replace the following line with your Model Studio API key: apiKey: "sk-xxx"
        apiKey: process.env.DASHSCOPE_API_KEY,
        // The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
        baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    }
);

const encodeVideo = (videoPath) => {
    const videoFile = readFileSync(videoPath);
    return videoFile.toString('base64');
  };
// Replace xxx/test.mp4 with the absolute path of your local video
const base64Video = encodeVideo("xxx/test.mp4")
async function main() {
    const completion = await openai.chat.completions.create({
        model: "qwen3-vl-plus",  
        messages: [
            {"role": "user",
             "content": [{
                 // When passing a video file directly, set the value of type to video_url.
                "type": "video_url", 
                "video_url": {"url": `data:video/mp4;base64,${base64Video}`}},
                 {"type": "text", "text": "What does this video depict?"}]}]
    });
    console.log(completion.choices[0].message.content);
}

main();

# ======= Important =======
# API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# === Delete this comment before execution ===

curl --location 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
  "model": "qwen3-vl-plus",
  "messages": [
  {
    "role": "user",
    "content": [
      {"type": "video_url", "video_url": {"url": "data:video/mp4;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAA..."}},
      {"type": "text", "text": "What is depicted in the image?"}
    ]
  }]
}'

DashScope

import base64
import os
import dashscope

# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

# Encoding function: Converts a local file to a Base64-encoded string.
def encode_video(video_path):
    with open(video_path, "rb") as video_file:
        return base64.b64encode(video_file.read()).decode("utf-8")

# Replace xxxx/test.mp4 with the absolute path of your local video
base64_video = encode_video("xxxx/test.mp4")

messages = [{'role':'user',
                # The fps parameter controls the number of frames extracted from the video. It means one frame is extracted every 1/fps seconds.
             'content': [{'video': f"data:video/mp4;base64,{base64_video}","fps":2},
                            {'text': 'What does this video depict?'}]}]
response = dashscope.MultiModalConversation.call(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen3-vl-plus',
    messages=messages)

print(response.output.choices[0].message.content[0]["text"])

import java.io.IOException;
import java.util.*;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;

import com.alibaba.dashscope.aigc.multimodalconversation.*;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;

public class Main {

    static {
        // The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }
    
    private static String encodeVideoToBase64(String videoPath) throws IOException {
        Path path = Paths.get(videoPath);
        byte[] videoBytes = Files.readAllBytes(path);
        return Base64.getEncoder().encodeToString(videoBytes);
    }

    public static void callWithLocalFile(String localPath)
            throws ApiException, NoApiKeyException, UploadFileException, IOException {

        String base64Video = encodeVideoToBase64(localPath); // Base64 encoding

        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(new HashMap<String, Object>()
                                       {{
                                           put("video", "data:video/mp4;base64," + base64Video);// The fps parameter controls the number of frames extracted from the video. It means one frame is extracted every 1/fps seconds.
                                           put("fps", 2);
                                       }},
                        new HashMap<String, Object>(){{put("text", "What does this video depict?");}})).build();

        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If the environment variable is not configured, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")
                .messages(Arrays.asList(userMessage))
                .build();

        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }

    public static void main(String[] args) {
        try {
            // Replace xxx/test.mp4 with the absolute path of your local image
            callWithLocalFile("xxx/test.mp4");
        } catch (ApiException | NoApiKeyException | UploadFileException | IOException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

# ======= Important =======
# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen3-vl-plus",
    "input":{
        "messages":[
            {
             "role": "user",
             "content": [
               {"video": "data:video/mp4;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAA..."},
               {"text": "What is depicted in the image?"}
                ]
            }
        ]
    }
}'

Python

import os
import dashscope

# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

local_path1 = "football1.jpg"
local_path2 = "football2.jpg"
local_path3 = "football3.jpg"
local_path4 = "football4.jpg"

image_path1 = f"file://{local_path1}"
image_path2 = f"file://{local_path2}"
image_path3 = f"file://{local_path3}"
image_path4 = f"file://{local_path4}"

messages = [{'role':'user',
                # If the model is from the Qwen2.5-VL series and you pass an image list, you can set the fps parameter. This indicates that the image list is extracted from the original video every 1/fps seconds. This setting has no effect on other models.
             'content': [{'video': [image_path1,image_path2,image_path3,image_path4],"fps":2},
                         {'text': 'What does this video depict?'}]}]
response = MultiModalConversation.call(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen3-vl-plus',  # This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models
    messages=messages)

print(response.output.choices[0].message.content[0]["text"])

Java

// DashScope SDK version 2.18.3 or later is required.
import java.util.Arrays;
import java.util.Map;
import java.util.Collections;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;

public class Main {

    static {
        // The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }
    
    private static final String MODEL_NAME = "qwen3-vl-plus";  // This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models
    public static void videoImageListSample(String localPath1, String localPath2, String localPath3, String localPath4)
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        String filePath1 = "file://" + localPath1;
        String filePath2 = "file://" + localPath2;
        String filePath3 = "file://" + localPath3;
        String filePath4 = "file://" + localPath4;
        Map<String, Object> params = Map.of(
                "video", Arrays.asList(filePath1,filePath2,filePath3,filePath4),
                // If the model is from the Qwen2.5-VL series and you pass an image list, you can set the fps parameter. This indicates that the image list is extracted from the original video every 1/fps seconds. This setting has no effect on other models.
                "fps",2);
        MultiModalMessage userMessage = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(params,
                        Collections.singletonMap("text", "Describe the process shown in this video")))
                .build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If the environment variable is not configured, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model(MODEL_NAME)
                .messages(Arrays.asList(userMessage)).build();
        MultiModalConversationResult result = conv.call(param);
        System.out.print(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }
    public static void main(String[] args) {
        try {
            videoImageListSample(
                    "xxx/football1.jpg",
                    "xxx/football2.jpg",
                    "xxx/football3.jpg",
                    "xxx/football4.jpg");
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

OpenAI compatible

import os
from openai import OpenAI
import base64

# Encoding function: Converts a local file to a Base64-encoded string.
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")

base64_image1 = encode_image("football1.jpg")
base64_image2 = encode_image("football2.jpg")
base64_image3 = encode_image("football3.jpg")
base64_image4 = encode_image("football4.jpg")
client = OpenAI(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If the environment variable is not configured, replace the following line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
    model="qwen3-vl-plus",  # This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models
    messages=[  
    {"role": "user","content": [
        {"type": "video","video": [
            f"data:image/jpeg;base64,{base64_image1}",
            f"data:image/jpeg;base64,{base64_image2}",
            f"data:image/jpeg;base64,{base64_image3}",
            f"data:image/jpeg;base64,{base64_image4}",]},
        {"type": "text","text": "Describe the process shown in this video"},
    ]}]
)
print(completion.choices[0].message.content)

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

const openai = new OpenAI(
    {
        // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
        // If the environment variable is not configured, replace the following line with your Model Studio API key: apiKey: "sk-xxx"
        apiKey: process.env.DASHSCOPE_API_KEY,
        // The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope-intl.aliyuncs.com/compatible-mode/v1
        baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    }
);

const encodeImage = (imagePath) => {
    const imageFile = readFileSync(imagePath);
    return imageFile.toString('base64');
  };
  
const base64Image1 = encodeImage("football1.jpg")
const base64Image2 = encodeImage("football2.jpg")
const base64Image3 = encodeImage("football3.jpg")
const base64Image4 = encodeImage("football4.jpg")
async function main() {
    const completion = await openai.chat.completions.create({
        model: "qwen3-vl-plus",  // This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models
        messages: [
            {"role": "user",
             "content": [{"type": "video",
                            // Note: When passing Base64 data, the image format (image/{format}) must match the Content Type in the list of supported images.
                           // PNG image:  data:image/png;base64,${base64Image}
                          // JPEG image: data:image/jpeg;base64,${base64Image}
                         // WEBP image: data:image/webp;base64,${base64Image}
                        "video": [
                            `data:image/jpeg;base64,${base64Image1}`,
                            `data:image/jpeg;base64,${base64Image2}`,
                            `data:image/jpeg;base64,${base64Image3}`,
                            `data:image/jpeg;base64,${base64Image4}`]},
                        {"type": "text", "text": "What does this video depict?"}]}]
    });
    console.log(completion.choices[0].message.content);
}

main();

# ======= Important =======
# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen3-vl-plus",
    "messages": [{"role": "user",
                "content": [{"type": "video",
                "video": [
                          "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAA...",
                          "data:image/jpeg;base64,nEpp6jpnP57MoWSyOWwrkXMJhHRCWYeFYb...",
                          "data:image/jpeg;base64,JHWQnJPc40GwQ7zERAtRMK6iIhnWw4080s...",
                          "data:image/jpeg;base64,adB6QOU5HP7dAYBBOg/Fb7KIptlbyEOu58..."
                          ]},
                {"type": "text",
                "text": "Describe the process shown in this video"}]}]
}'

DashScope

import base64
import os
import dashscope

# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

# Encoding function: Converts a local file to a Base64-encoded string.
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")

base64_image1 = encode_image("football1.jpg")
base64_image2 = encode_image("football2.jpg")
base64_image3 = encode_image("football3.jpg")
base64_image4 = encode_image("football4.jpg")


messages = [{'role':'user',
            'content': [
                    {'video':
                         [f"data:image/png;base64,{base64_image1}",
                          f"data:image/png;base64,{base64_image2}",
                          f"data:image/png;base64,{base64_image3}",
                          f"data:image/png;base64,{base64_image4}"
                         ]
                    },
                    {'text': 'Please describe the process shown in this video.'}]}]
response = dashscope.MultiModalConversation.call(
    # API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model='qwen3-vl-plus',  # This example uses qwen3-vl-plus. You can replace it with another model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models
    messages=messages)

print(response.output.choices[0].message.content[0]["text"])

import java.io.IOException;
import java.util.*;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;

import com.alibaba.dashscope.aigc.multimodalconversation.*;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;

public class Main {

    static {
        // The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }

    private static String encodeImageToBase64(String imagePath) throws IOException {
        Path path = Paths.get(imagePath);
        byte[] imageBytes = Files.readAllBytes(path);
        return Base64.getEncoder().encodeToString(imageBytes);
    }

    public static void videoImageListSample(String localPath1,String localPath2,String localPath3,String localPath4)
            throws ApiException, NoApiKeyException, UploadFileException, IOException {

        String base64Image1 = encodeImageToBase64(localPath1); // Base64 encoding
        String base64Image2 = encodeImageToBase64(localPath2);
        String base64Image3 = encodeImageToBase64(localPath3);
        String base64Image4 = encodeImageToBase64(localPath4);

        MultiModalConversation conv = new MultiModalConversation();
        Map<String, Object> params = Map.of(
                "video", Arrays.asList(
                        "data:image/jpeg;base64," + base64Image1,
                        "data:image/jpeg;base64," + base64Image2,
                        "data:image/jpeg;base64," + base64Image3,
                        "data:image/jpeg;base64," + base64Image4),
                // If the model is from the Qwen2.5-VL series and you pass an image list, you can set the fps parameter. This indicates that the image list is extracted from the original video every 1/fps seconds. This setting has no effect on other models.
                    "fps",2
        );
        MultiModalMessage userMessage = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(params,
                        Collections.singletonMap("text", "Describe the process shown in this video")))
                .build();

        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")
                .messages(Arrays.asList(userMessage))
                .build();

        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }

    public static void main(String[] args) {
        try {
            // Replace xxx/football1.png and other paths with the absolute paths of your local images
            videoImageListSample(
                    "xxx/football1.jpg",
                    "xxx/football2.jpg",
                    "xxx/football3.jpg",
                    "xxx/football4.jpg"
            );
        } catch (ApiException | NoApiKeyException | UploadFileException | IOException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

# ======= Important =======
# The following is the base_url for the Singapore region. If you use a model in the Beijing region, replace the base_url with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# API keys for the Singapore and Beijing regions are different. To get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# === Delete this comment before execution ===

curl -X POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
  "model": "qwen3-vl-plus",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "video": [
                      "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAA...",
                      "data:image/jpeg;base64,nEpp6jpnP57MoWSyOWwrkXMJhHRCWYeFYb...",
                      "data:image/jpeg;base64,JHWQnJPc40GwQ7zERAtRMK6iIhnWw4080s...",
                      "data:image/jpeg;base64,adB6QOU5HP7dAYBBOg/Fb7KIptlbyEOu58..."
            ],
            "fps":2     
          },
          {
            "text": "Describe the process shown in this video"
          }
        ]
      }
    ]
  }
}'