Skip to main content
Toolkit/Framework

Compatível com OpenAI - Visão

Os modelos de visão do Qwen no Alibaba Cloud Model Studio são compatíveis com a especificação da interface OpenAI. Para migrar suas aplicações OpenAI existentes para o Model Studio, modifique apenas três parâmetros:

  • base_url:
    • China (Pequim): https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
    • Singapura: https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1. Substitua {WorkspaceId} pelo seu ID do workspace real.
    • Japão (Tóquio): https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/compatible-mode/v1. Substitua {WorkspaceId} pelo ID do seu workspace real.
    • EUA (Virgínia): https://dashscope-us.aliyuncs.com/compatible-mode/v1
    • China (Hong Kong): https://{WorkspaceId}.cn-hongkong.maas.aliyuncs.com/compatible-mode/v1. Substitua WorkspaceId pelo seu ID do workspace real.
  • api_key: Substitua pela sua chave de API do Model Studio
  • model: Substitua por um nome de modelo da lista a seguir
O Model Studio lançou domínios específicos por workspace para as regiões China (Pequim), Singapura e China (Hong Kong). Os novos domínios dedicados oferecem desempenho superior e maior estabilidade para solicitações de inferência. Recomendamos migrar para os novos domínios:
  • China (Pequim): de https://dashscope.aliyuncs.com para https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com
  • Singapura: de https://dashscope-intl.aliyuncs.com para https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com
  • China (Hong Kong): de https://cn-hongkong.dashscope.aliyuncs.com para https://{WorkspaceId}.cn-hongkong.maas.aliyuncs.com
{WorkspaceId} é o ID do seu workspace, disponível na página Workspace Details no console do Model Studio. O domínio existente permanece totalmente funcional.

Modelos compatíveis

Modelos compatíveis: Qwen-VL, QVQ, Qwen-OCR
Os modelos disponíveis variam conforme a região. Para mais detalhes, consulte o console do Model Studio .

Invocação do modelo

Exemplos

Esta seção apresenta exemplos de chamadas em streaming para Python (OpenAI SDK e LangChain_OpenAI SDK) e cURL (HTTP). Para outras linguagens de programação ou exemplos de métodos de entrada, consulte Exemplos de solicitação de visão.
Os modelos QVQ aceitam apenas saída em streaming. Para mais detalhes, consulte Raciocínio visual .
  • OpenAI SDK
from openai import OpenAI
import os

def get_response():
    client = OpenAI(
    # API keys vary by region. Obtain an API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Singapore base_url. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)
    completion = client.chat.completions.create(
        model="qwen3-vl-plus",
        messages=[
            {
              "role": "user",
              "content": [
                {
                  "type": "text",
                  "text": "What is this"
                },
                {
                  "type": "image_url",
                  "image_url": {
                    "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
                  }
                }
              ]
            }
          ],
        stream=True,
        stream_options={"include_usage":True}
        )
    for chunk in completion:
        print(chunk.model_dump())

if __name__=='__main__':
    get_response()
A execução do código produz o seguinte resultado: 
{'id': 'chatcmpl-31042a05-c968-4fc6-ba28-c3aa471258dc', 'choices': [{'delta': {'content': '', 'function_call': None, 'refusal': None, 'role': 'assistant', 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1765780318, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-31042a05-c968-4fc6-ba28-c3aa471258dc', 'choices': [{'delta': {'content': 'This', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1765780318, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-31042a05-c968-4fc6-ba28-c3aa471258dc', 'choices': [{'delta': {'content': ' photo', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1765780318, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-31042a05-c968-4fc6-ba28-c3aa471258dc', 'choices': [{'delta': {'content': ' shows', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1765780318, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}

......

{'id': 'chatcmpl-31042a05-c968-4fc6-ba28-c3aa471258dc', 'choices': [{'delta': {'content': ' moment', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1765780318, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-31042a05-c968-4fc6-ba28-c3aa471258dc', 'choices': [{'delta': {'content': '.', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}], 'created': 1765780318, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-31042a05-c968-4fc6-ba28-c3aa471258dc', 'choices': [{'delta': {'content': '', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': 'stop', 'index': 0, 'logprobs': None}], 'created': 1765780318, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': None}
{'id': 'chatcmpl-31042a05-c968-4fc6-ba28-c3aa471258dc', 'choices': [], 'created': 1765780318, 'model': 'qwen-vl-plus', 'object': 'chat.completion.chunk', 'service_tier': None, 'system_fingerprint': None, 'usage': {'completion_tokens': 230, 'prompt_tokens': 1259, 'total_tokens': 1489, 'completion_tokens_details': {'accepted_prediction_tokens': None, 'audio_tokens': None, 'reasoning_tokens': None, 'rejected_prediction_tokens': None, 'text_tokens': 230}, 'prompt_tokens_details': {'audio_tokens': None, 'cached_tokens': 0}}}

LangChain OpenAI SDK

Pré-requisitos

  • Verifique se o Python está instalado no seu computador.
  • Instale o SDK langchain_openai executando o comando a seguir. 
# If the following command fails, replace pip with pip3
pip install -U langchain_openai
  • Ative o Model Studio e obtenha uma chave de API. Para mais detalhes, consulte Obter uma chave de API.
  • Recomendamos configurar a chave de API como variável de ambiente para reduzir o risco de vazamento. Para mais detalhes, consulte Configurar chave de API como variável de ambiente. Também é possível definir a chave de API diretamente no código, mas isso aumenta o risco de vazamento.

Uso

Use os exemplos a seguir para chamar modelos de visão do Qwen por meio do SDK langchain_openai.

Saída sem streaming

A saída sem streaming utiliza o método invoke. Consulte o código de exemplo a seguir: 
from langchain_openai import ChatOpenAI
import os

def get_response():
    llm = ChatOpenAI(
      # API keys vary by region. Obtain an API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
      api_key=os.getenv("DASHSCOPE_API_KEY"),
      # China (Beijing) URL. URLs vary by region.
      base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
      model="qwen3-vl-plus",
      )
    messages= [
            {
              "role": "user",
              "content": [
                {
                  "type": "text",
                  "text": "What is this"
                },
                {
                  "type": "image_url",
                  "image_url": {
                    "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
                  }
                }
              ]
            }
          ]
    response = llm.invoke(messages)
    print(response.content)

if __name__ == "__main__":
    get_response()

from langchain_openai import ChatOpenAI
import os

def get_response():
    llm = ChatOpenAI(
      # API keys vary by region. Obtain an API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
      api_key=os.getenv("DASHSCOPE_API_KEY"),
      # Singapore base_url. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
      base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
      model="qwen3-vl-plus",
      )
    messages= [
            {
              "role": "user",
              "content": [
                {
                  "type": "text",
                  "text": "What is this"
                },
                {
                  "type": "image_url",
                  "image_url": {
                    "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
                  }
                }
              ]
            }
          ]
    response = llm.invoke(messages)
    print(response.content)

if __name__ == "__main__":
    get_response()
A execução do código produz o seguinte resultado: 
{
  “content”: “This photo shows a woman and a dog interacting warmly on a beach. Here is a detailed description:\n\n1. **Scene**:\n   - The photo is taken on a beach with the ocean and sky in the background.\n   - The sun is about to set or has just risen, casting warm golden light on the sand.\n\n2. **Person**:\n   - A woman is sitting on the sand, wearing a plaid shirt and dark pants.\n   - She is smiling, appearing very happy and relaxed.\n\n3. **Animal**:\n   - A yellow Labrador retriever is sitting next to the woman.\n   - The dog is wearing a colorful harness and appears healthy and friendly.\n   - The dog has placed its paw gently on the woman's hand, as if performing a \”handshake\” gesture.\n\n4. **Interaction**:\n   - The interaction between the woman and the dog appears very intimate and joyful.\n   - This interaction showcases the deep bond between humans and their pets.\n\n5. **Atmosphere**:\n   - The overall atmosphere is very serene and beautiful, giving a sense of relaxation and happiness.\n   - The sound of waves and the beauty of the sunset add a romantic touch to this scene.\n\nThis photo captures a simple and beautiful moment, showcasing the harmonious relationship between humans and their pets, as well as the tranquility and beauty that nature brings.”,
  "additional_kwargs": {
    "refusal": null
  },
  "response_metadata": {
    "token_usage": {
      "completion_tokens": 267,
      "prompt_tokens": 1259,
      "total_tokens": 1526,
      "completion_tokens_details": {
        "accepted_prediction_tokens": null,
        "audio_tokens": null,
        "reasoning_tokens": null,
        "rejected_prediction_tokens": null,
        "text_tokens": 267
      },
      "prompt_tokens_details": {
        "audio_tokens": null,
        "cached_tokens": 0
      }
    },
    "model_provider": "openai",
    "model_name": "qwen-vl-plus",
    "system_fingerprint": null,
    "id": "chatcmpl-9f3eba85-4f7a-4f73-b254-220a650xxxxx",
    "finish_reason": "stop",
    "logprobs": null
  },
  "type": "ai",
  "name": null,
  "id": "lc_run--019b1191-f411-7153-ac51-b8b0410xxxxx-0",
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 1259,
    "output_tokens": 267,
    "total_tokens": 1526,
    "input_token_details": {
      "cache_read": 0
    },
    "output_token_details": {}
  }
}

Saída em streaming

Os exemplos a seguir não se aplicam aos modelos QVQ. Para uso do QVQ, consulte Raciocínio visual . 
from langchain_openai import ChatOpenAI
import os

def get_response():
    llm = ChatOpenAI(
        # API keys vary by region. Obtain an API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # China (Beijing) URL. URLs vary by region.
        base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
        model="qwen3-vl-plus",
        # Display token usage information in the last line of streaming output
        stream_options={"include_usage": True}
    )
    messages= [
            {
              "role": "user",
              "content": [
                {
                  "type": "text",
                  "text": "What is this"
                },
                {
                  "type": "image_url",
                  "image_url": {
                    "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
                  }
                }
              ]
            }
          ]
    response = llm.stream(messages)
    for chunk in response:
        print(chunk.content)

if __name__ == "__main__":
    get_response()

from langchain_openai import ChatOpenAI
import os

def get_response():
    llm = ChatOpenAI(
        # API keys vary by region. Obtain an API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # Singapore base_url. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
        base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
        model="qwen3-vl-plus",
        # Display token usage information in the last line of streaming output
        stream_options={"include_usage": True}
    )
    messages= [
            {
              "role": "user",
              "content": [
                {
                  "type": "text",
                  "text": "What is this"
                },
                {
                  "type": "image_url",
                  "image_url": {
                    "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
                  }
                }
              ]
            }
          ]
    response = llm.stream(messages)
    for chunk in response:
        print(chunk.json())

if __name__ == "__main__":
    get_response()
A execução do código produz o seguinte resultado de exemplo: 
{"content": "", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": "This", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " image", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " shows", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " a dog", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " and a young", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " girl. The dog looks", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " friendly and is likely", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " a pet, while the girl", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " seems to be interacting", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " or playing with the dog.", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " This is an image depicting", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " the warm bond between", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " humans and animals.", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": "", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": "", "additional_kwargs": {}, "response_metadata": {"finish_reason": "stop"}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": "", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": {"input_tokens": 23, "output_tokens": 40, "total_tokens": 63}, "tool_call_chunks": []}
Para configurar os parâmetros de entrada, consulte Parâmetros. Os parâmetros relacionados estão definidos no objeto ChatOpenAI.

HTTP

Chame modelos de visão do Qwen pela interface HTTP e obtenha respostas com a mesma estrutura das chamadas aos serviços OpenAI via HTTP.

Pré-requisitos

  • Ative o Model Studio e obtenha uma chave de API. Para mais detalhes, consulte Obter uma chave de API.
  • Recomendamos configurar a chave de API como variável de ambiente para reduzir o risco de vazamento. Para mais detalhes, consulte Configurar chave de API como variável de ambiente. Também é possível definir a chave de API diretamente no código, mas isso aumenta o risco de vazamento.

Endpoints da API 

China (Beijing): POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions
Singapore: POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
Japan (Tokyo): POST https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
US (Virginia): POST https://dashscope-us.aliyuncs.com/compatible-mode/v1/chat/completions

Singapore: POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
Japan (Tokyo): POST https://{WorkspaceId}.ap-northeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
US (Virginia): POST https://dashscope-us.aliyuncs.com/compatible-mode/v1/chat/completions
China (Beijing): POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
China (Hong Kong): POST https://cn-hongkong.{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions

Exemplos de solicitação

Os exemplos a seguir mostram como chamar a API usando comandos cURL.
Caso não tenha configurado a chave de API como variável de ambiente, substitua $DASHSCOPE_API_KEY pela sua chave de API*.*

Saída sem streaming 

# ======= Important =======
# API keys vary by region. Obtain an API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# Singapore URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.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": "text",
          "text": "What are these"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
          }
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"
          }
        }
      ]
    }
  ]
}'
A execução do comando produz o seguinte resultado: 
{
  "choices": [
    {
      "message": {
        "content": "Image 1 shows a woman and her pet dog interacting on the beach, with the dog raising its front paw as if trying to shake hands.\nImage 2 is a CG-rendered image of a tiger.",
        "role": "assistant"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 2509,
    "completion_tokens": 34,
    "total_tokens": 2543
  },
  "created": 1724729556,
  "system_fingerprint": null,
  "model": "qwen-vl-plus",
  "id": "chatcmpl-1abb4eb9-f508-9637-a8ba-ac7fc6f73e53"
}

Saída em streaming

Para usar saída em streaming, defina o parâmetro stream como true no corpo da solicitação. 
# ======= Important =======
# API keys vary by region. Obtain an API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# China (Beijing) URL. URLs vary by region.

curl --location 'https://{WorkspaceId}.cn-beijing.maas.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": "text",
          "text": "What is this"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
          }
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true}
}'

# ======= Important =======
# API keys vary by region. Obtain an API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# Singapore URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.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": "text",
          "text": "What is this"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
          }
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true}
}'
A execução do comando produz o seguinte resultado: 
data: {"choices":[{"delta":{"content":"","role":"assistant"},"index":0,"logprobs":null,"finish_reason":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"finish_reason":null,"delta":{"content":"The"},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"delta":{"content":" image"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"delta":{"content":" shows a woman"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"delta":{"content":" and her dog on"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"delta":{"content":" the beach. The dog is sitting,"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"delta":{"content":" reaching out its paw as if to shake"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"delta":{"content":" hands. The woman is wearing a plaid"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"delta":{"content":" shirt and appears to be closely"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"delta":{"content":" interacting with the dog, smiling."},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"delta":{"content":" The background features the ocean and a sunrise"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"delta":{"content":" or sunset sky. This is a"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"delta":{"content":" warm and heartfelt photo, capturing a"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[{"finish_reason":"stop","delta":{"content":" moment of friendship between humans and pets."},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: {"choices":[],"object":"chat.completion.chunk","usage":{"prompt_tokens":1276,"completion_tokens":79,"total_tokens":1355},"created":1724729595,"system_fingerprint":null,"model":"qwen-vl-plus","id":"chatcmpl-4c83f437-303f-907b-9de5-79cac83d6b18"}

data: [DONE]
Para obter detalhes sobre os parâmetros de entrada, consulte Parâmetros.

Exemplo de resposta de erro

Se a solicitação falhar, a resposta incluirá os campos code e message indicando a causa do erro. 
{
    "error": {
        "message": "Incorrect API key provided. ",
        "type": "invalid_request_error",
        "param": null,
        "code": "invalid_api_key"
    }
}

Códigos de status

Para obter informações sobre códigos de status, consulte Códigos de status.
Uso da API
Referência da API de Geração de Texto
Geração de Imagens
  • FAQ
Geração de Vídeo
Áudio
Multimodal em Tempo Real
API em tempo real
Incorporação de Texto
Mais Modelos
Toolkit/Framework
Produção de Modelos
File Management
Gerenciamento de modelos
Mais