Skip to main content
Visual understanding

Raciocínio visual

Os modelos de raciocínio visual apresentam o processo de pensamento antes de responder. Use-os para tarefas visuais complexas: problemas matemáticos, análise de gráficos ou compreensão de vídeo.

Demonstração

O componente acima serve apenas para demonstração e não envia solicitações reais.

Modelos compatíveis

  • Qwen3.7
    • Modelos de pensamento híbrido: qwen3.7-plus, qwen3.7-plus-2026-05-26
  • Qwen3.6
    • Modelos de pensamento híbrido: qwen3.6-plus, qwen3.6-plus-2026-04-02, qwen3.6-flash, qwen3.6-flash-2026-04-16, qwen3.6-35b-a3b
  • Qwen3.5
    • Modelos de pensamento híbrido: qwen3.5-plus, qwen3.5-plus-2026-02-15, qwen3.5-flash, qwen3.5-flash-2026-02-23, qwen3.5-397b-a17b, qwen3.5-122b-a10b, qwen3.5-27b, qwen3.5-35b-a3b
  • Qwen3-VL
    • Modelos de pensamento híbrido: qwen3-vl-plus, qwen3-vl-plus-2025-12-19, qwen3-vl-plus-2025-09-23, qwen3-vl-flash, qwen3-vl-flash-2025-10-15
    • Modelos exclusivos de pensamento: qwen3-vl-235b-a22b-thinking,qwen3-vl-32b-thinking,qwen3-vl-30b-a3b-thinking,qwen3-vl-8b-thinking
  • QVQ
    • Modelos exclusivos de pensamento: série qvq-max, série qvq-plus
  • Kimi
    • Modelos de pensamento híbrido: kimi-k2.6, kimi-k2.5

Guia de uso

  • Processo de pensamento: O Model Studio oferece dois tipos de modelos de raciocínio visual: pensamento híbrido e exclusivo de pensamento.
    • Modelos de pensamento híbrido: Controle o pensamento com o parâmetro enable_thinking:
      • Defina como true: gera primeiro o processo de pensamento e depois a resposta final (padrão para as séries Qwen3.6 e Qwen3.5).
      • Defina como false: gera a resposta diretamente (padrão para as séries qwen3-vl-plus, qwen3-vl-flash).
    • Modelos exclusivos de pensamento: Estes modelos sempre geram um processo de pensamento antes de fornecer uma resposta. Não é possível desativar esse comportamento.
  • Método de saída: Use streaming para evitar timeouts causados por processos de pensamento longos.
    • Qwen3.6, Qwen3.5, Qwen3-VL, kimi-k2.6, kimi-k2.5 e stepfun/step-3.7-flash aceitam os métodos streaming e não-streaming.
    • A série QVQ aceita apenas saída em streaming.
  • Recomendações de prompt do sistema:
    • Conversas simples ou de turno único: Não defina System Message. Passe instruções (como função e formato) via User Message para obter melhores resultados de inferência.
    • Aplicações complexas (agentes, chamadas de ferramentas): Use System Message para definir a função do modelo, as capacidades e a estrutura comportamental.

Primeiros passos

Pré-requisitos Os exemplos abaixo chamam qvq-max para resolver um problema matemático a partir de uma imagem. Eles usam streaming para imprimir separadamente o processo de pensamento e a resposta final.
  • OpenAI compatible
  • DashScope
  • Python
  • Node.js
  • HTTP
from openai import OpenAI
import os

# Initialize the OpenAI client
client = OpenAI(
    # API keys differ by region. To obtain one, see https://modelstudio.console.alibabacloud.com/?tab=model#/api-key
    # If not configured, replace with: api_key="sk-xxx"
    api_key = os.getenv("DASHSCOPE_API_KEY"),
    # Replace {WorkspaceId} with your workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
)

reasoning_content = ""  # Define the full thinking process
answer_content = ""     # Define the full response
is_answering = False   # Check if the thinking process has ended and the response has started

# Create a chat completion request
completion = client.chat.completions.create(
    model="qvq-max",  # Example uses qvq-max. Replace with other model names as needed.
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"
                    },
                },
                {"type": "text", "text": "How do I solve this problem?"},
            ],
        },
    ],
    stream=True,
    # Uncomment the following to return token usage in the last chunk
    # stream_options={
    #     "include_usage": True
    # }
)

print("\n" + "=" * 20 + "Thinking process" + "=" * 20 + "\n")

for chunk in completion:
    # If chunk.choices is empty, print the usage
    if not chunk.choices:
        print("\nUsage:")
        print(chunk.usage)
    else:
        delta = chunk.choices[0].delta
        # Print the thinking process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
            print(delta.reasoning_content, end='', flush=True)
            reasoning_content += delta.reasoning_content
        else:
            # Start responding
            if delta.content != "" and is_answering is False:
                print("\n" + "=" * 20 + "Full response" + "=" * 20 + "\n")
                is_answering = True
            # Print the response process
            print(delta.content, end='', flush=True)
            answer_content += delta.content

# print("=" * 20 + "Full thinking process" + "=" * 20 + "\n")
# print(reasoning_content)
# print("=" * 20 + "Full response" + "=" * 20 + "\n")
# print(answer_content)

Capacidades principais

Ativar ou desativar o processo de pensamento

Para cenários que exigem pensamento detalhado (resolução de problemas, análise de relatórios), ative o modo de pensamento usando o parâmetro enable_thinking conforme mostrado abaixo.
  • OpenAI compatible
  • DashScope
enable_thinking e thinking_budget são parâmetros não padrão da OpenAI. A forma de passagem de parâmetros varia conforme a linguagem:
  • SDK Python: É necessário passá-los pelo dicionário extra_body.
  • SDK Node.js: Passe-os diretamente como parâmetros de nível superior.
from openai import OpenAI
import os

# Initialize the OpenAI client
client = OpenAI(
    # If you have not configured an environment variable, replace the following line with your Alibaba Cloud Model Studio API key: api_key="sk-xxx",
    # API keys differ by region. 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 is the base URL for the Beijing region. If you are using a model in the US (Virginia) region, replace the base_url with https://dashscope-us.aliyuncs.com/compatible-mode/v1
    # The URL below is for the China (Beijing) region. URLs vary by region.
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)

reasoning_content = ""  # Define the full thinking process
answer_content = ""     # Define the full response
is_answering = False   # Check if the thinking process has ended and the response has started
enable_thinking = True
# Create a chat completion request
completion = client.chat.completions.create(
    model="qwen3.5-plus",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"
                    },
                },
                {"type": "text", "text": "How do I solve this problem?"},
            ],
        },
    ],
    stream=True,
    # The enable_thinking parameter enables the thinking process. The thinking_budget parameter sets the maximum number of tokens for the reasoning process.
    # For qwen3.5-plus, qwen3-vl-plus, and qwen3-vl-flash, you can use enable_thinking to enable or disable thinking (qwen3.5-plus is enabled by default). For models with the 'thinking' suffix, such as qwen3-vl-235b-a22b-thinking, enable_thinking can only be set to true. This parameter does not apply to other Qwen-VL models.
    extra_body={
        'enable_thinking': enable_thinking},

    # Uncomment the following to return token usage in the last chunk
    # stream_options={
    #     "include_usage": True
    # }
)

if enable_thinking:
    print("\n" + "=" * 20 + "Thinking process" + "=" * 20 + "\n")

for chunk in completion:
    # If chunk.choices is empty, print the usage
    if not chunk.choices:
        print("\nUsage:")
        print(chunk.usage)
    else:
        delta = chunk.choices[0].delta
        # Print the thinking process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
            print(delta.reasoning_content, end='', flush=True)
            reasoning_content += delta.reasoning_content
        else:
            # Start responding
            if delta.content != "" and is_answering is False:
                print("\n" + "=" * 20 + "Full response" + "=" * 20 + "\n")
                is_answering = True
            # Print the response process
            print(delta.content, end='', flush=True)
            answer_content += delta.content

# print("=" * 20 + "Full thinking process" + "=" * 20 + "\n")
# print(reasoning_content)
# print("=" * 20 + "Full response" + "=" * 20 + "\n")
# print(answer_content)

import OpenAI from "openai";

// Initialize the OpenAI client
const openai = new OpenAI({
     // If no environment variable configured: api_key="sk-xxx",
    // API keys differ by region. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    apiKey: process.env.DASHSCOPE_API_KEY,
    // The following is the base URL for the Beijing region. If you are using a model in the US (Virginia) region, replace the base_url with https://dashscope-us.aliyuncs.com/compatible-mode/v1
    // The URL below is for the China (Beijing) region. URLs vary by region.
    baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
});

let reasoningContent = '';
let answerContent = '';
let isAnswering = false;
let enableThinking = true;

let messages = [
    {
        role: "user",
        content: [
        { type: "image_url", image_url: { "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg" } },
        { type: "text", text: "Solve this problem" },
    ]
}]

async function main() {
    try {
        const stream = await openai.chat.completions.create({
            model: 'qwen3.5-plus',
            messages: messages,
            stream: true,
          // Note: In Node.js SDK, non-standard parameters (like enableThinking) pass as top-level properties, not in extra_body.
          enable_thinking: enableThinking

        });

        if (enableThinking){console.log('\n' + '='.repeat(20) + 'Thinking process' + '='.repeat(20) + '\n');}

        for await (const chunk of stream) {
            if (!chunk.choices?.length) {
                console.log('\nUsage:');
                console.log(chunk.usage);
                continue;
            }

            const delta = chunk.choices[0].delta;

            // Handle the thinking process
            if (delta.reasoning_content) {
                process.stdout.write(delta.reasoning_content);
                reasoningContent += delta.reasoning_content;
            }
            // Handle the formal response
            else if (delta.content) {
                if (!isAnswering) {
                    console.log('\n' + '='.repeat(20) + 'Full response' + '='.repeat(20) + '\n');
                    isAnswering = true;
                }
                process.stdout.write(delta.content);
                answerContent += delta.content;
            }
        }
    } catch (error) {
        console.error('Error:', error);
    }
}

main();

# ======= IMPORTANT =======
# API keys differ by region. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the base URL for the Beijing region. If you are using a model in the US (Virginia) region, replace the base_url with https://dashscope-us.aliyuncs.com/compatible-mode/v1/chat/completions
# The URL below is for the China (Beijing) region. URLs vary by region.
# === Delete this comment before execution ===

curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3.5-plus",
    "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"
          }
        },
        {
          "type": "text",
          "text": "Solve this problem"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true},
    "enable_thinking": true
}'

import os
from openai import OpenAI

client = OpenAI(
    # API keys differ by region. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Replace {WorkspaceId} with your workspace ID. URLs vary by region.
    # If you are using a model in the Beijing region, replace the base_url with https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
)

reasoning_content = ""  # Define the full thinking process
answer_content = ""     # Define the full response
is_answering = False   # Check if the thinking process has ended and the response has started
enable_thinking = True
# Create a chat completion request
completion = client.chat.completions.create(
    model="qwen3.5-plus",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"
                    },
                },
                {"type": "text", "text": "How do I solve this problem?"},
            ],
        },
    ],
    stream=True,
    # The enable_thinking parameter enables the thinking process. The thinking_budget parameter sets the maximum number of tokens for the reasoning process.
    # For qwen3.5-plus, qwen3-vl-plus, and qwen3-vl-flash, you can use enable_thinking to enable or disable thinking (qwen3.5-plus is enabled by default). For models with the 'thinking' suffix, such as qwen3-vl-235b-a22b-thinking, enable_thinking can only be set to true. This parameter does not apply to other Qwen-VL models.
    extra_body={
        'enable_thinking': enable_thinking
        },

    # Uncomment the following to return token usage in the last chunk
    # stream_options={
    #     "include_usage": True
    # }
)

if enable_thinking:
    print("\n" + "=" * 20 + "Thinking process" + "=" * 20 + "\n")

for chunk in completion:
    # If chunk.choices is empty, print the usage
    if not chunk.choices:
        print("\nUsage:")
        print(chunk.usage)
    else:
        delta = chunk.choices[0].delta
        # Print the thinking process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
            print(delta.reasoning_content, end='', flush=True)
            reasoning_content += delta.reasoning_content
        else:
            # Start responding
            if delta.content != "" and is_answering is False:
                print("\n" + "=" * 20 + "Full response" + "=" * 20 + "\n")
                is_answering = True
            # Print the response process
            print(delta.content, end='', flush=True)
            answer_content += delta.content

# print("=" * 20 + "Full thinking process" + "=" * 20 + "\n")
# print(reasoning_content)
# print("=" * 20 + "Full response" + "=" * 20 + "\n")
# print(answer_content)

import OpenAI from "openai";

// Initialize the OpenAI client
const openai = new OpenAI({
  // API keys differ by region. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
  // If no environment variable configured: apiKey: "sk-xxx"
  apiKey: process.env.DASHSCOPE_API_KEY,
 // Replace {WorkspaceId} with your workspace ID. URLs vary by region.
 //  If you are using a model in the Beijing region, replace the base_url with https://dashscope.aliyuncs.com/compatible-mode/v1
  baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

let reasoningContent = '';
let answerContent = '';
let isAnswering = false;
let enableThinking = true;

let messages = [
    {
        role: "user",
        content: [
        { type: "image_url", image_url: { "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg" } },
        { type: "text", text: "Solve this problem" },
    ]
}]

async function main() {
    try {
        const stream = await openai.chat.completions.create({
            model: 'qwen3.5-plus',
            messages: messages,
            stream: true,
          // Note: In Node.js SDK, non-standard parameters (like enableThinking) pass as top-level properties, not in extra_body.
          enable_thinking: enableThinking

        });

        if (enableThinking){console.log('\n' + '='.repeat(20) + 'Thinking process' + '='.repeat(20) + '\n');}

        for await (const chunk of stream) {
            if (!chunk.choices?.length) {
                console.log('\nUsage:');
                console.log(chunk.usage);
                continue;
            }

            const delta = chunk.choices[0].delta;

            // Handle the thinking process
            if (delta.reasoning_content) {
                process.stdout.write(delta.reasoning_content);
                reasoningContent += delta.reasoning_content;
            }
            // Handle the formal response
            else if (delta.content) {
                if (!isAnswering) {
                    console.log('\n' + '='.repeat(20) + 'Full response' + '='.repeat(20) + '\n');
                    isAnswering = true;
                }
                process.stdout.write(delta.content);
                answerContent += delta.content;
            }
        }
    } catch (error) {
        console.error('Error:', error);
    }
}

main();

# ======= IMPORTANT =======
# Replace {WorkspaceId} with your workspace ID. URLs vary by region.
# If you are using a model in the Beijing region, replace the base_url with https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# API keys differ by region. 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://{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": "qwen3.5-plus",
    "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"
          }
        },
        {
          "type": "text",
          "text": "Solve this problem"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true},
    "enable_thinking": true
}'

Limitar o tamanho do pensamento

Use o parâmetro thinking_budget para limitar o comprimento em tokens do processo de pensamento. Se o limite for excedido, o conteúdo será truncado e o modelo gerará imediatamente a resposta final. O valor padrão corresponde ao comprimento máximo de cadeia de pensamento do modelo. Para mais informações, consulte a Lista de modelos.
O parâmetro thinking_budget é compatível com Qwen3.6, Qwen3.5, Qwen3-VL (modo de pensamento), kimi-k2.5 (modo de pensamento) e kimi-k2.6 (modo de pensamento).
  • OpenAI compatible
  • DashScope
thinking_budget é um parâmetro não padrão da OpenAI. Ao usar o SDK Python da OpenAI, passe-o através de extra_body.
from openai import OpenAI
import os

# Initialize the OpenAI client
client = OpenAI(
    # If you have not configured an environment variable, replace the following line with your Alibaba Cloud Model Studio API key: api_key="sk-xxx",
    # API keys differ by region. 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 is the base URL for the Beijing region. If you are using a model in the US (Virginia) region, replace the base_url with https://dashscope-us.aliyuncs.com/compatible-mode/v1
    # The URL below is for the China (Beijing) region. URLs vary by region.
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)

reasoning_content = ""  # Define the full thinking process
answer_content = ""     # Define the full response
is_answering = False   # Check if the thinking process has ended and the response has started
enable_thinking = True
# Create a chat completion request
completion = client.chat.completions.create(
    model="qwen3.5-plus",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"
                    },
                },
                {"type": "text", "text": "How do I solve this problem?"},
            ],
        },
    ],
    stream=True,
    # The enable_thinking parameter enables the thinking process. The thinking_budget parameter sets the maximum number of tokens for the reasoning process.
    # For qwen3.5-plus, qwen3-vl-plus, and qwen3-vl-flash, you can use enable_thinking to enable or disable thinking (qwen3.5-plus is enabled by default). For models with the 'thinking' suffix, such as qwen3-vl-235b-a22b-thinking, enable_thinking can only be set to true. This parameter does not apply to other Qwen-VL models.
    extra_body={
        'enable_thinking': enable_thinking,
        "thinking_budget": 81920},

    # Uncomment the following to return token usage in the last chunk
    # stream_options={
    #     "include_usage": True
    # }
)

if enable_thinking:
    print("\n" + "=" * 20 + "Thinking process" + "=" * 20 + "\n")

for chunk in completion:
    # If chunk.choices is empty, print the usage
    if not chunk.choices:
        print("\nUsage:")
        print(chunk.usage)
    else:
        delta = chunk.choices[0].delta
        # Print the thinking process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
            print(delta.reasoning_content, end='', flush=True)
            reasoning_content += delta.reasoning_content
        else:
            # Start responding
            if delta.content != "" and is_answering is False:
                print("\n" + "=" * 20 + "Full response" + "=" * 20 + "\n")
                is_answering = True
            # Print the response process
            print(delta.content, end='', flush=True)
            answer_content += delta.content

# print("=" * 20 + "Full thinking process" + "=" * 20 + "\n")
# print(reasoning_content)
# print("=" * 20 + "Full response" + "=" * 20 + "\n")
# print(answer_content)

import OpenAI from "openai";

// Initialize the OpenAI client
const openai = new OpenAI({
     // If no environment variable configured: api_key="sk-xxx",
    // API keys differ by region. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    apiKey: process.env.DASHSCOPE_API_KEY,
    // The following is the base URL for the Beijing region. If you are using a model in the US (Virginia) region, replace the base_url with https://dashscope-us.aliyuncs.com/compatible-mode/v1
    // The URL below is for the China (Beijing) region. URLs vary by region.
    baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1'
});

let reasoningContent = '';
let answerContent = '';
let isAnswering = false;
let enableThinking = true;

let messages = [
    {
        role: "user",
        content: [
        { type: "image_url", image_url: { "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg" } },
        { type: "text", text: "Solve this problem" },
    ]
}]

async function main() {
    try {
        const stream = await openai.chat.completions.create({
            model: 'qwen3.5-plus',
            messages: messages,
            stream: true,
          // Note: In Node.js SDK, non-standard parameters (like enableThinking) pass as top-level properties, not in extra_body.
          enable_thinking: enableThinking,
          thinking_budget: 81920

        });

        if (enableThinking){console.log('\n' + '='.repeat(20) + 'Thinking process' + '='.repeat(20) + '\n');}

        for await (const chunk of stream) {
            if (!chunk.choices?.length) {
                console.log('\nUsage:');
                console.log(chunk.usage);
                continue;
            }

            const delta = chunk.choices[0].delta;

            // Handle the thinking process
            if (delta.reasoning_content) {
                process.stdout.write(delta.reasoning_content);
                reasoningContent += delta.reasoning_content;
            }
            // Handle the formal response
            else if (delta.content) {
                if (!isAnswering) {
                    console.log('\n' + '='.repeat(20) + 'Full response' + '='.repeat(20) + '\n');
                    isAnswering = true;
                }
                process.stdout.write(delta.content);
                answerContent += delta.content;
            }
        }
    } catch (error) {
        console.error('Error:', error);
    }
}

main();

# ======= IMPORTANT =======
# API keys differ by region. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# The following is the base URL for the Beijing region. If you are using a model in the US (Virginia) region, replace the base_url with https://dashscope-us.aliyuncs.com/compatible-mode/v1/chat/completions
# The URL below is for the China (Beijing) region. URLs vary by region.
# === Delete this comment before execution ===

curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3.5-plus",
    "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"
          }
        },
        {
          "type": "text",
          "text": "Solve this problem"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true},
    "enable_thinking": true,
    "thinking_budget": 81920
}'

import os
from openai import OpenAI

client = OpenAI(
    # API keys differ by region. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Replace {WorkspaceId} with your workspace ID. URLs vary by region.
    # If you are using a model in the Beijing region, replace the base_url with https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
)

reasoning_content = ""  # Define the full thinking process
answer_content = ""     # Define the full response
is_answering = False   # Check if the thinking process has ended and the response has started
enable_thinking = True
# Create a chat completion request
completion = client.chat.completions.create(
    model="qwen3.5-plus",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"
                    },
                },
                {"type": "text", "text": "How do I solve this problem?"},
            ],
        },
    ],
    stream=True,
    # The enable_thinking parameter enables the thinking process. The thinking_budget parameter sets the maximum number of tokens for the reasoning process.
    # For qwen3.5-plus, qwen3-vl-plus, and qwen3-vl-flash, you can use enable_thinking to enable or disable thinking (qwen3.5-plus is enabled by default). For models with the 'thinking' suffix, such as qwen3-vl-235b-a22b-thinking, enable_thinking can only be set to true. This parameter does not apply to other Qwen-VL models.
    extra_body={
        'enable_thinking': enable_thinking,
        "thinking_budget": 81920},

    # Uncomment the following to return token usage in the last chunk
    # stream_options={
    #     "include_usage": True
    # }
)

if enable_thinking:
    print("\n" + "=" * 20 + "Thinking process" + "=" * 20 + "\n")

for chunk in completion:
    # If chunk.choices is empty, print the usage
    if not chunk.choices:
        print("\nUsage:")
        print(chunk.usage)
    else:
        delta = chunk.choices[0].delta
        # Print the thinking process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
            print(delta.reasoning_content, end='', flush=True)
            reasoning_content += delta.reasoning_content
        else:
            # Start responding
            if delta.content != "" and is_answering is False:
                print("\n" + "=" * 20 + "Full response" + "=" * 20 + "\n")
                is_answering = True
            # Print the response process
            print(delta.content, end='', flush=True)
            answer_content += delta.content

# print("=" * 20 + "Full thinking process" + "=" * 20 + "\n")
# print(reasoning_content)
# print("=" * 20 + "Full response" + "=" * 20 + "\n")
# print(answer_content)

import OpenAI from "openai";

// Initialize the OpenAI client
const openai = new OpenAI({
  // API keys differ by region. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
  // If no environment variable configured: apiKey: "sk-xxx"
  apiKey: process.env.DASHSCOPE_API_KEY,
  // Replace {WorkspaceId} with your workspace ID. URLs vary by region.
  // If you are using a model in the Beijing region, replace the base_url with https://dashscope.aliyuncs.com/compatible-mode/v1
  baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

let reasoningContent = '';
let answerContent = '';
let isAnswering = false;
let enableThinking = true;

let messages = [
    {
        role: "user",
        content: [
        { type: "image_url", image_url: { "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg" } },
        { type: "text", text: "Solve this problem" },
    ]
}]

async function main() {
    try {
        const stream = await openai.chat.completions.create({
            model: 'qwen3.5-plus',
            messages: messages,
            stream: true,
          // Note: In Node.js SDK, non-standard parameters (like enableThinking) pass as top-level properties, not in extra_body.
          enable_thinking: enableThinking,
          thinking_budget: 81920

        });

        if (enableThinking){console.log('\n' + '='.repeat(20) + 'Thinking process' + '='.repeat(20) + '\n');}

        for await (const chunk of stream) {
            if (!chunk.choices?.length) {
                console.log('\nUsage:');
                console.log(chunk.usage);
                continue;
            }

            const delta = chunk.choices[0].delta;

            // Handle the thinking process
            if (delta.reasoning_content) {
                process.stdout.write(delta.reasoning_content);
                reasoningContent += delta.reasoning_content;
            }
            // Handle the formal response
            else if (delta.content) {
                if (!isAnswering) {
                    console.log('\n' + '='.repeat(20) + 'Full response' + '='.repeat(20) + '\n');
                    isAnswering = true;
                }
                process.stdout.write(delta.content);
                answerContent += delta.content;
            }
        }
    } catch (error) {
        console.error('Error:', error);
    }
}

main();

# ======= IMPORTANT =======
# Replace {WorkspaceId} with your workspace ID. URLs vary by region.
# If you are using a model in the Beijing region, replace the base_url with https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# API keys differ by region. 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://{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": "qwen3.5-plus",
    "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"
          }
        },
        {
          "type": "text",
          "text": "Solve this problem"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true},
    "enable_thinking": true,
    "thinking_budget": 81920
}'

Mais exemplos

Os modelos de raciocínio visual aceitam todos os recursos de compreensão visual para cenários complexos, como:

Faturamento

Custo total = (Tokens de entrada × Preço por token de entrada) + (Tokens de saída × Preço por token de saída).
  • O processo de pensamento (reasoning_content) é cobrado como tokens de saída. Caso não haja saída de pensamento, aplica-se o preço do modo sem pensamento.
  • Para o cálculo de tokens de imagens/vídeos, consulte Compreensão de imagem e vídeo.

Referência da API

Para os parâmetros de entrada e saída, consulte Geração de texto.

Códigos de erro

Se a chamada do modelo falhar e retornar uma mensagem de erro, consulte Códigos de erro para resolução.
Começar
Faturamento
Plano de Tokens
Playground de Modelos
Clientes e Ferramentas de Desenvolvedor
Inferência do Modelo
Ajuste fino
Implantação
Avaliação
Compressão de Modelos
Estatísticas e Monitoramento
Segurança e Conformidade
Melhores Práticas
Suporte
Registro de alterações