Document Center
 
All Products
Search
  • Document Center
  • Alibaba Cloud Model Studio
  • Panduan Pengguna (model)
  • Inference
  • Pembuatan teks
  • Penalaran visual

This Product

  • This Product
  • All Products

    Alibaba Cloud Model Studio:Penalaran visual

    Document Center

    Alibaba Cloud Model Studio:Penalaran visual

    Last Updated:Mar 18, 2026

    Model penalaran visual menghasilkan proses pemikirannya sebelum memberikan jawaban akhir. Model ini cocok untuk tugas analisis visual kompleks, seperti menyelesaikan soal matematika, menganalisis data grafik, atau memahami video yang rumit.

    Contoh

    QVQ Logo
    Penalaran Visual
    Komponen di atas hanya untuk tujuan demonstrasi dan tidak mengirim permintaan nyata.

    Penerapan

    Wilayah yang didukung

    • Singapura: Gunakan API key untuk wilayah ini.

    • AS (Virginia): Gunakan API key untuk wilayah ini.

    • Beijing: Gunakan API key untuk wilayah ini.

    • Hong Kong (Tiongkok): Gunakan API key untuk wilayah ini.

    Model yang didukung

    • Qwen3.5

      • Model hybrid-thinking: 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

      • Model hybrid-thinking: qwen3-vl-plus, qwen3-vl-plus-2025-12-19, qwen3-vl-plus-2025-09-23, qwen3-vl-flash, qwen3-vl-flash-2025-10-15

      • Model thinking-only: qwen3-vl-235b-a22b-thinking, qwen3-vl-32b-thinking, qwen3-vl-30b-a3b-thinking, qwen3-vl-8b-thinking

    • QVQ

      Model thinking-only: seri qvq-max, seri qvq-plus

    • Kimi

      Model hybrid-thinking: kimi-k2.5

    Panduan penggunaan

    • Proses pemikiran: Alibaba Cloud Model Studio menyediakan model penalaran visual, termasuk tipe hybrid dan reasoning-only.

      • Model hybrid-thinking: Anda dapat mengontrol perilaku pemikiran menggunakan parameter enable_thinking:

        • Atur parameter ini ke true untuk mengaktifkan pemikiran. Model pertama kali mengeluarkan proses pemikirannya lalu respons akhir. Nilai default untuk seri qwen3.5-plus adalah true.

        • Atur parameter ini ke false untuk menonaktifkan pemikiran. Model langsung menghasilkan respons. Nilai default untuk seri qwen3-vl-plus dan qwen3-vl-flash adalah false.

      • Model thinking-only: Model ini selalu menghasilkan proses pemikiran sebelum merespons, dan perilaku ini tidak dapat dinonaktifkan.

    • Metode output: Model penalaran visual mencakup proses pemikiran yang detail. Untuk menghindari timeout akibat respons panjang, Anda dapat menggunakan keluaran streaming.

      • Qwen3.5, Qwen3-VL, dan kimi-k2.5 mendukung metode streaming dan non-streaming.

      • Seri QVQ hanya mendukung keluaran streaming.

    • Rekomendasi prompt sistem:

      • Untuk percakapan single-turn atau sederhana: Jangan atur System Message. Untuk hasil inferensi optimal, Anda dapat memberikan instruksi—seperti definisi peran dan format output—melalui User Message.

      • Untuk aplikasi kompleks seperti membangun agen atau tool calling: Anda dapat menggunakan System Message untuk mendefinisikan peran, kemampuan, dan kerangka perilaku model guna memastikan stabilitas dan keandalan.

    Mulai cepat

    Prasyarat

    • Dapatkan API key dan konfigurasikan sebagai variabel lingkungan.

    • Jika Anda menggunakan SDK, instal versi SDK terbaru. DashScope Python SDK harus versi 1.24.6 atau lebih baru, dan DashScope Java SDK harus versi 2.21.10 atau lebih baru.

    Contoh berikut menunjukkan cara memanggil model qvq-max untuk menyelesaikan soal matematika dari gambar. Contoh menggunakan keluaran streaming untuk mencetak proses pemikiran dan respons akhir secara terpisah.

    Kompatibel dengan OpenAI

    Python

    from openai import OpenAI
    import os
    
    # Inisialisasi klien OpenAI
    client = OpenAI(
        # API key berbeda tiap wilayah. Dapatkan di https://bailian.console.alibabacloud.com/?tab=model#/api-key
        # Jika Anda belum mengonfigurasi variabel lingkungan, ganti dengan Kunci API Model Studio Anda: api_key="sk-xxx"
        api_key = os.getenv("DASHSCOPE_API_KEY"),
        # URL dasar Singapura. Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/compatible-mode/v1       
        base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    )
    
    reasoning_content = ""  # Definisikan proses pemikiran lengkap
    answer_content = ""     # Definisikan respons lengkap
    is_answering = False   # Periksa apakah proses pemikiran telah berakhir dan respons telah dimulai
    
    # Buat permintaan chat completion
    completion = client.chat.completions.create(
        model="qvq-max",  # Contoh menggunakan qvq-max. Ganti dengan nama model lain sesuai kebutuhan.
        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,
        # Hapus komentar berikut untuk mengembalikan penggunaan token pada chunk terakhir
        # stream_options={
        #     "include_usage": True
        # }
    )
    
    print("\n" + "=" * 20 + "Thinking process" + "=" * 20 + "\n")
    
    for chunk in completion:
        # Jika chunk.choices kosong, cetak penggunaan
        if not chunk.choices:
            print("\nUsage:")
            print(chunk.usage)
        else:
            delta = chunk.choices[0].delta
            # Cetak proses pemikiran
            if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
                print(delta.reasoning_content, end='', flush=True)
                reasoning_content += delta.reasoning_content
            else:
                # Mulai merespons
                if delta.content != "" and is_answering is False:
                    print("\n" + "=" * 20 + "Full response" + "=" * 20 + "\n")
                    is_answering = True
                # Cetak proses respons
                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)

    Node.js

    import OpenAI from "openai";
    import process from 'process';
    
    // Inisialisasi klien OpenAI
    const openai = new OpenAI({
        apiKey: process.env.DASHSCOPE_API_KEY, // Baca dari variabel lingkungan. API key berbeda tiap wilayah. Dapatkan di https://bailian.console.alibabacloud.com/?tab=model#/api-key
        // URL dasar Singapura. Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/compatible-mode/v1       
        baseURL: 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1'
    });
    
    let reasoningContent = '';
    let answerContent = '';
    let isAnswering = false;
    
    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: 'qvq-max',
                messages: messages,
                stream: true
            });
    
            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;
    
                // Tangani proses pemikiran
                if (delta.reasoning_content) {
                    process.stdout.write(delta.reasoning_content);
                    reasoningContent += delta.reasoning_content;
                }
                // Tangani respons formal
                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();

    Klik untuk melihat proses pemikiran dan respons lengkap

    ====================Thinking process====================
    
    Okay, I need to solve this problem about the surface area and volume of a rectangular prism and a cube. First, I need to carefully look at the problem to make sure I understand the requirements for each part.
    
    The problem asks to calculate the surface area and volume of two shapes separately. The first shape is a rectangular prism, and the second is a cube. The units are all in centimeters, and each question is worth 6 points, for a total of 12 points. This looks like a math homework problem, possibly from elementary or middle school geometry.
    
    First, I need to recall the formulas for the surface area and volume of a rectangular prism and a cube. For a rectangular prism, the formula for surface area is: \( 2(ab + bc + ac) \), where a, b, and c are the length, width, and height, respectively. The volume is \( abc \). For a cube, because all side lengths are equal, the surface area is \( 6a^2 \), and the volume is \( a^3 \).
    
    Now, let's look at the first shape, a rectangular prism with given dimensions of length 4 cm, width 3 cm, and height 2 cm. I need to calculate its surface area first. Plugging the values into the formula:
    
    Surface Area = \( 2(4×3 + 3×2 + 4×2) \)
            = \( 2(12 + 6 + 8) \)
            = \( 2×26 \)
            = 52 cm²
    
    Next is the volume, again plugging in the values:
    
    Volume = \( 4×3×2 \)
          = 24 cm³
    
    Then, for the second shape, a cube with a side length of 3 cm. The surface area is calculated as follows:
    
    Surface Area = \( 6×3^2 \)
            = \( 6×9 \)
            = 54 cm²
    
    And the volume is:
    
    Volume = \( 3^3 \)
          = 27 cm³
    
    However, I need to check for any potential mistakes. For example, in calculating the surface area of the rectangular prism, did I miscalculate the area of any face? Or did I make a mistake in the multiplication?
    
    For instance, the three different faces of the rectangular prism are 4×3, 3×2, and 4×2. The areas of these faces are 12, 6, and 8. Adding them up gives 26, and multiplying by 2 gives 52, which should be correct. For the volume, 4×3=12, and then multiplying by 2 is 24, which is also correct.
    
    For the cube, each face is 3×3=9, and with six faces, the total is 54. The volume is 3×3×3=27, which is also correct.
    
    So the final answers should be:
    
    1. The surface area of the rectangular prism is 52 square centimeters, and the volume is 24 cubic centimeters.
    2. The surface area of the cube is 54 square centimeters, and the volume is 27 cubic centimeters.
    
    However, I need to confirm if there is any other hidden information or potential traps in the figures in the problem. For example, sometimes problems might include dashed lines or shaded areas, but in this case, the rectangular prism and cube in the image look standard, with no special markings. Therefore, I believe my calculations are correct.
    
    ====================Full response====================
    
    ### Solution:
    
    **1. Rectangular Prism (length 4 cm, width 3 cm, height 2 cm)**
    - **Surface Area**:
      \[
      2 \times (4 \times 3 + 3 \times 2 + 4 \times 2) = 2 \times (12 + 6 + 8) = 2 \times 26 = 52 \, \text{cm}^2
      \]
    - **Volume**:
      \[
      4 \times 3 \times 2 = 24 \, \text{cm}^3
      \]
    
    **2. Cube (side length 3 cm)**
    - **Surface Area**:
      \[
      6 \times 3^2 = 6 \times 9 = 54 \, \text{cm}^2
      \]
    - **Volume**:
      \[
      3^3 = 27 \, \text{cm}^3
      \]
    
    **Answer:**
    1. The surface area of the rectangular prism is \(52 \, \text{cm}^2\), and its volume is \(24 \, \text{cm}^3\).
    2. The surface area of the cube is \(54 \, \text{cm}^2\), and its volume is \(27 \, \text{cm}^3\).
    

    HTTP

    # ======= IMPORTANT =======
    # Berikut adalah URL dasar untuk wilayah Singapura. Jika Anda menggunakan model di wilayah Beijing, ganti base_url dengan https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions    
    # API key berbeda tiap wilayah. Dapatkan di https://bailian.console.alibabacloud.com/?tab=model#/api-key
    # === Hapus komentar ini sebelum eksekusi ===
    
    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": "qvq-max",
        "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}
    }'

    Klik untuk melihat proses pemikiran dan respons lengkap

    data: {"choices":[{"delta":{"content":null,"role":"assistant","reasoning_content":""},"index":0,"logprobs":null,"finish_reason":null}],"object":"chat.completion.chunk","usage":null,"created":1742983020,"system_fingerprint":null,"model":"qvq-max","id":"chatcmpl-ab4f3963-2c2a-9291-bda2-65d5b325f435"}
    
    data: {"choices":[{"finish_reason":null,"delta":{"content":null,"reasoning_content":"Okay"},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1742983020,"system_fingerprint":null,"model":"qvq-max","id":"chatcmpl-ab4f3963-2c2a-9291-bda2-65d5b325f435"}
    
    data: {"choices":[{"delta":{"content":null,"reasoning_content":","},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1742983020,"system_fingerprint":null,"model":"qvq-max","id":"chatcmpl-ab4f3963-2c2a-9291-bda2-65d5b325f435"}
    
    data: {"choices":[{"delta":{"content":null,"reasoning_content":" I am now"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1742983020,"system_fingerprint":null,"model":"qvq-max","id":"chatcmpl-ab4f3963-2c2a-9291-bda2-65d5b325f435"}
    
    data: {"choices":[{"delta":{"content":null,"reasoning_content":" going to"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1742983020,"system_fingerprint":null,"model":"qvq-max","id":"chatcmpl-ab4f3963-2c2a-9291-bda2-65d5b325f435"}
    
    data: {"choices":[{"delta":{"content":null,"reasoning_content":" solve"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1742983020,"system_fingerprint":null,"model":"qvq-max","id":"chatcmpl-ab4f3963-2c2a-9291-bda2-65d5b325f435"}
    .....
    data: {"choices":[{"delta":{"content":"square "},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1742983095,"system_fingerprint":null,"model":"qvq-max","id":"chatcmpl-23d30959-42b4-9f24-b7ab-1bb0f72ce265"}
    
    data: {"choices":[{"delta":{"content":"centimeters"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1742983095,"system_fingerprint":null,"model":"qvq-max","id":"chatcmpl-23d30959-42b4-9f24-b7ab-1bb0f72ce265"}
    
    data: {"choices":[{"finish_reason":"stop","delta":{"content":"","reasoning_content":null},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1742983095,"system_fingerprint":null,"model":"qvq-max","id":"chatcmpl-23d30959-42b4-9f24-b7ab-1bb0f72ce265"}
    
    data: {"choices":[],"object":"chat.completion.chunk","usage":{"prompt_tokens":544,"completion_tokens":590,"total_tokens":1134,"completion_tokens_details":{"text_tokens":590},"prompt_tokens_details":{"text_tokens":24,"image_tokens":520}},"created":1742983095,"system_fingerprint":null,"model":"qvq-max","id":"chatcmpl-23d30959-42b4-9f24-b7ab-1bb0f72ce265"}
    
    data: [DONE]

    DashScope

    Catatan

    Memanggil model QVQ melalui DashScope:

    • Parameter incremental_output secara default bernilai true dan tidak dapat diatur ke false. Hanya streaming inkremental yang didukung.

    • Parameter result_format secara default bernilai "message" dan tidak dapat diatur ke "text".

    Python

    import os
    import dashscope
    from dashscope import MultiModalConversation
    
    # Berikut adalah URL dasar untuk wilayah Singapura. Jika Anda menggunakan model di wilayah Beijing, ganti base_url dengan https://dashscope.aliyuncs.com/api/v1      
    dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'
    messages = [
        {
            "role": "user",
            "content": [
                {"image": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"},
                {"text": "How do I solve this problem?"}
            ]
        }
    ]
    
    response = MultiModalConversation.call(
        # API key berbeda tiap wilayah. Dapatkan di https://bailian.console.alibabacloud.com/?tab=model#/api-key
        # Jika Anda belum mengonfigurasi variabel lingkungan, ganti baris berikut dengan Kunci API Model Studio Anda: api_key="sk-xxx",
        api_key=os.getenv('DASHSCOPE_API_KEY'),
        model="qvq-max",  # Contoh menggunakan qvq-max. Ganti dengan nama model lain sesuai kebutuhan.
        messages=messages,
        stream=True,
    )
    
    # Definisikan proses pemikiran lengkap
    reasoning_content = ""
    # Definisikan respons lengkap
    answer_content = ""
    # Periksa apakah proses pemikiran telah berakhir dan respons telah dimulai
    is_answering = False
    
    print("=" * 20 + "Thinking process" + "=" * 20)
    
    for chunk in response:
        # Jika proses pemikiran dan respons keduanya kosong, abaikan
        message = chunk.output.choices[0].message
        reasoning_content_chunk = message.get("reasoning_content", None)
        if (chunk.output.choices[0].message.content == [] and
            reasoning_content_chunk == ""):
            pass
        else:
            # Jika sedang dalam proses pemikiran
            if reasoning_content_chunk != None and chunk.output.choices[0].message.content == []:
                print(chunk.output.choices[0].message.reasoning_content, end="")
                reasoning_content += chunk.output.choices[0].message.reasoning_content
            # Jika sedang dalam respons
            elif chunk.output.choices[0].message.content != []:
                if not is_answering:
                    print("\n" + "=" * 20 + "Full response" + "=" * 20)
                    is_answering = True
                print(chunk.output.choices[0].message.content[0]["text"], end="")
                answer_content += chunk.output.choices[0].message.content[0]["text"]
    
    # Untuk mencetak proses pemikiran dan respons lengkap, hapus komentar dan jalankan kode berikut
    # print("=" * 20 + "Full thinking process" + "=" * 20 + "\n")
    # print(f"{reasoning_content}")
    # print("=" * 20 + "Full response" + "=" * 20 + "\n")
    # print(f"{answer_content}")

    Klik untuk melihat proses pemikiran dan respons lengkap

    ====================Thinking process====================
    Okay, I need to solve this problem about the surface area and volume of a rectangular prism and a cube. First, I need to carefully look at the problem to make sure I understand the requirements for each part.
    
    The problem asks to calculate the surface area and volume of two shapes separately. The first shape is a rectangular prism, and the second is a cube. The units are all in centimeters, and each question is worth 6 points, for a total of 12 points. This looks like a math homework problem, possibly from elementary or middle school geometry.
    
    First, I need to recall the formulas for the surface area and volume of a rectangular prism and a cube. For a rectangular prism, the formula for surface area is: \( Area = 2(ab + bc + ac) \), where a, b, and c are the length, width, and height, respectively. The volume is: \( Volume = abc \). For a cube, because all side lengths are equal, the surface area is: \( Area = 6a^2 \), and the volume is: \( Volume = a^3 \).
    
    Now, let's look at the first shape, a rectangular prism with given dimensions of length 4 cm, width 3 cm, and height 2 cm. I need to first confirm that these values correspond correctly to the variables in the formula. Usually, the three dimensions of a rectangular prism can be named arbitrarily, but for convenience, we can consider the longest side as the length, the middle one as the width, and the shortest as the height. However, in this case, the problem has clearly labeled the lengths of each side, so I can use them directly.
    
    Next, I'll calculate the surface area of the first rectangular prism. Plugging the values into the formula:
    
    \( Area = 2(4×3 + 3×2 + 4×2) \)
    
    First, calculate each term inside the parentheses:
    
    \( 4×3 = 12 \)
    \( 3×2 = 6 \)
    \( 4×2 = 8 \)
    
    Then, add these results together:
    
    \( 12 + 6 + 8 = 26 \)
    
    And multiply by 2:
    
    \( 2 × 26 = 52 \)
    
    So, the surface area of the first rectangular prism is 52 square centimeters.
    
    Next, calculate the volume:
    
    \( Volume = 4 × 3 × 2 = 24 \)
    
    So, the volume is 24 cubic centimeters.
    
    Now, let's look at the second shape, a cube with all side lengths of 3 cm. Therefore, the surface area calculation is:
    
    \( Area = 6 × 3^2 = 6 × 9 = 54 \)
    
    And the volume is:
    
    \( Volume = 3^3 = 27 \)
    
    So, the surface area of the cube is 54 square centimeters, and the volume is 27 cubic centimeters.
    
    During the calculation, I need to pay attention to the consistency of units. The unit given in the problem is centimeters, so the final results should be in square centimeters and cubic centimeters. Also, I need to ensure there are no calculation errors, such as the order of multiplication and addition, especially when calculating the surface area of the rectangular prism, where it's easy to miss a term or make a calculation mistake.
    
    Additionally, I'll check for any other possible misunderstandings, such as whether the length, width, and height are correctly identified. But in this problem, because the lengths of each side are clearly labeled, this should not be an issue. Also, for the cube, all side lengths are equal, so there's no complexity from different side lengths.
    
    To summarize, the surface area of the first rectangular prism is 52 square centimeters, and its volume is 24 cubic centimeters. The surface area of the second cube is 54 square centimeters, and its volume is 27 cubic centimeters.
    
    ====================Full response====================
    ### Solution:
    
    **1. Rectangular Prism (length 4 cm, width 3 cm, height 2 cm)**
    
    - **Surface Area**:
      \[
      Area = 2(ab + bc + ac) = 2(4×3 + 3×2 + 4×2) = 2(12 + 6 + 8) = 2×26 = 52 \, \text{cm}^2
      \]
    
    - **Volume**:
      \[
      Volume = abc = 4×3×2 = 24 \, \text{cm}^3
      \]
    
    **2. Cube (side length 3 cm)**
    
    - **Surface Area**:
      \[
      Area = 6a^2 = 6×3^2 = 6×9 = 54 \, \text{cm}^2
      \]
    
    - **Volume**:
      \[
      Volume = a^3 = 3^3 = 27 \, \text{cm}^3
      \]
    
    **Answer:**
    1. The surface area of the rectangular prism is \(52 \, \text{cm}^2\), and its volume is \(24 \, \text{cm}^3\).
    2. The surface area of the cube is \(54 \, \text{cm}^2\), and its volume is \(27 \, \text{cm}^3\).
    

    Java

    // DashScope SDK version >= 2.19.0
    import java.util.*;
    
    import org.slf4j.Logger;
    import org.slf4j.LoggerFactory;
    
    import com.alibaba.dashscope.common.Role;
    import com.alibaba.dashscope.exception.ApiException;
    import com.alibaba.dashscope.exception.NoApiKeyException;
    import io.reactivex.Flowable;
    
    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.exception.UploadFileException;
    import com.alibaba.dashscope.exception.InputRequiredException;
    import java.lang.System;
    import com.alibaba.dashscope.utils.Constants;
    
    public class Main {
        static {
           // Berikut adalah URL dasar untuk wilayah Singapura. Jika Anda menggunakan model di wilayah Beijing, ganti base_url dengan https://dashscope.aliyuncs.com/api/v1      
            Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
        }
        private static final Logger logger = LoggerFactory.getLogger(Main.class);
        private static StringBuilder reasoningContent = new StringBuilder();
        private static StringBuilder finalContent = new StringBuilder();
        private static boolean isFirstPrint = true;
    
        private static void handleGenerationResult(MultiModalConversationResult message) {
            String re = message.getOutput().getChoices().get(0).getMessage().getReasoningContent();
            String reasoning = Objects.isNull(re)?"":re; // Default value
    
            List<Map<String, Object>> content = message.getOutput().getChoices().get(0).getMessage().getContent();
            if (!reasoning.isEmpty()) {
                reasoningContent.append(reasoning);
                if (isFirstPrint) {
                    System.out.println("====================Thinking process====================");
                    isFirstPrint = false;
                }
                System.out.print(reasoning);
            }
    
            if (Objects.nonNull(content) && !content.isEmpty()) {
                Object text = content.get(0).get("text");
                finalContent.append(content.get(0).get("text"));
                if (!isFirstPrint) {
                    System.out.println("\n====================Full response====================");
                    isFirstPrint = true;
                }
                System.out.print(text);
            }
        }
        public static MultiModalConversationParam buildMultiModalConversationParam(MultiModalMessage Msg)  {
            return MultiModalConversationParam.builder()
                    // API key berbeda tiap wilayah. Dapatkan di https://bailian.console.alibabacloud.com/?tab=model#/api-key
                    // Jika Anda belum mengonfigurasi variabel lingkungan, ganti baris berikut dengan Kunci API Model Studio Anda: .apiKey("sk-xxx")
                    .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                    // Contoh menggunakan qvq-max. Ganti dengan nama model lain sesuai kebutuhan.
                    .model("qvq-max")
                    .messages(Arrays.asList(Msg))
                    .incrementalOutput(true)
                    .build();
        }
    
        public static void streamCallWithMessage(MultiModalConversation conv, MultiModalMessage Msg)
                throws NoApiKeyException, ApiException, InputRequiredException, UploadFileException {
            MultiModalConversationParam param = buildMultiModalConversationParam(Msg);
            Flowable<MultiModalConversationResult> result = conv.streamCall(param);
            result.blockingForEach(message -> {
                handleGenerationResult(message);
            });
        }
        public static void main(String[] args) {
            try {
                MultiModalConversation conv = new MultiModalConversation();
                MultiModalMessage userMsg = MultiModalMessage.builder()
                        .role(Role.USER.getValue())
                        .content(Arrays.asList(Collections.singletonMap("image", "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"),
                                Collections.singletonMap("text", "Solve this problem")))
                        .build();
                streamCallWithMessage(conv, userMsg);
    //             Cetak hasil akhir
    //            if (reasoningContent.length() > 0) {
    //                System.out.println("\n====================Full response====================");
    //                System.out.println(finalContent.toString());
    //            }
            } catch (ApiException | NoApiKeyException | UploadFileException | InputRequiredException e) {
                logger.error("An exception occurred: {}", e.getMessage());
            }
            System.exit(0);
        }
    }

    Klik untuk melihat proses pemikiran dan respons lengkap

    ====================Thinking process====================
    Hmm, I need to solve this problem, which is to calculate the surface area and volume of two shapes. First, I need to carefully examine the image provided in the problem. The first shape is a rectangular prism, and the second is a cube. The problem asks to calculate their surface area and volume separately, with units in centimeters.
    
    Let's look at the first shape, the rectangular prism. Its dimensions should be length, width, and height. According to the labels on the image, the length is 4 cm, the width is 3 cm, and the height is 2 cm. Right? I remember the formula for the surface area of a rectangular prism is 2 times (length × width + length × height + width × height). And the volume is length times width times height. Let me double-check if the formula is correct. Yes, the surface area is indeed the sum of the areas of the six faces, and because opposite faces have equal areas, this formula is correct.
    
    So, plugging in the values, the surface area should be 2×(4×3 + 4×2 + 3×2). First, calculate the terms inside the parentheses: 4×3=12, 4×2=8, 3×2=6. Adding them up gives 12+8+6=26. Then multiplying by 2 gives 52 square centimeters. For the volume, 4×3×2=24 cubic centimeters. This part should be correct.
    
    Next is the second shape, the cube. All its side lengths are 3 cm. The surface area of a cube is 6 times the square of the side length, because it has six identical square faces. The volume is the cube of the side length. So the surface area should be 6×3²=6×9=54 square centimeters. The volume is 3³=27 cubic centimeters. I need to pay attention to the units here. The problem states the unit is cm, so the results should be written in square centimeters and cubic centimeters.
    
    However, I should double-check if I made any mistakes. For example, are the sides of the rectangular prism correctly identified? In the image, the length of the rectangular prism does look longer than its width, so length is 4, width is 3, and height is 2. For the cube, all three dimensions are 3, which is fine. Did I make any calculation errors? For example, in the surface area calculation for the rectangular prism, are the products correct, and is the addition correct? For instance, 4×3=12, 4×2=8, 3×2=6, adding up to 26, and multiplying by 2 is 52, which is correct. The volume 4×3×2=24 is also correct. For the cube, the surface area 6×9=54 and volume 27 are also correct.
    
    One thing to note is the units. The problem clearly states the unit is cm, so I should add the correct unit symbols to the answers. Also, the problem states that each question is worth 6 points, for a total of 12 points, but there are only two questions, so each is worth 6 points. This doesn't affect the calculation process, but it's a reminder not to miss any steps or units.
    
    To summarize, the surface area of the first shape is 52 square centimeters, and its volume is 24 cubic centimeters; the surface area of the second shape is 54 square centimeters, and its volume is 27 cubic centimeters. That should be it.
    
    ====================Full response====================
    **Answer:**
    
    1. **Rectangular Prism**  
       - **Surface Area**: \(2 \times (4 \times 3 + 4 \times 2 + 3 \times 2) = 2 \times 26 = 52\) square centimeters  
       - **Volume**: \(4 \times 3 \times 2 = 24\) cubic centimeters  
    
    2. **Cube**  
       - **Surface Area**: \(6 \times 3^2 = 6 \times 9 = 54\) square centimeters  
       - **Volume**: \(3^3 = 27\) cubic centimeters  
    
    **Explanation:**  
    - The surface area of a rectangular prism is obtained by calculating the total area of its six faces, and its volume is the product of its length, width, and height.  
    - The surface area of a cube is the sum of the areas of its six identical square faces, and its volume is the cube of its side length.  
    - All units are in centimeters, as required by the problem.

    HTTP

    curl

    # ======= IMPORTANT =======
    # Berikut adalah URL dasar untuk wilayah Singapura. Jika Anda menggunakan model di wilayah Beijing, ganti base_url dengan https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation       
    # API key berbeda tiap wilayah. Dapatkan di https://bailian.console.alibabacloud.com/?tab=model#/api-key
    # === Hapus komentar ini sebelum eksekusi ===
    
    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' \
    -H 'X-DashScope-SSE: enable' \
    -d '{
        "model": "qvq-max",
        "input":{
            "messages":[
                {
                    "role": "user",
                    "content": [
                        {"image": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"},
                        {"text": "Solve this problem"}
                    ]
                }
            ]
        }
    }'

    Klik untuk melihat proses pemikiran dan respons lengkap

    id:1
    event:result
    :HTTP_STATUS/200
    data:{"output":{"choices":[{"message":{"content":[],"reasoning_content":"Okay","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":547,"input_tokens_details":{"image_tokens":520,"text_tokens":24},"output_tokens":3,"input_tokens":544,"output_tokens_details":{"text_tokens":3},"image_tokens":520},"request_id":"f361ae45-fbef-9387-9f35-1269780e0864"}
    
    id:2
    event:result
    :HTTP_STATUS/200
    data:{"output":{"choices":[{"message":{"content":[],"reasoning_content":",","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":548,"input_tokens_details":{"image_tokens":520,"text_tokens":24},"output_tokens":4,"input_tokens":544,"output_tokens_details":{"text_tokens":4},"image_tokens":520},"request_id":"f361ae45-fbef-9387-9f35-1269780e0864"}
    
    id:3
    event:result
    :HTTP_STATUS/200
    data:{"output":{"choices":[{"message":{"content":[],"reasoning_content":" I am now","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":549,"input_tokens_details":{"image_tokens":520,"text_tokens":24},"output_tokens":5,"input_tokens":544,"output_tokens_details":{"text_tokens":5},"image_tokens":520},"request_id":"f361ae45-fbef-9387-9f35-1269780e0864"}
    .....
    id:566
    event:result
    :HTTP_STATUS/200
    data:{"output":{"choices":[{"message":{"content":[{"text":"square"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":1132,"input_tokens_details":{"image_tokens":520,"text_tokens":24},"output_tokens":588,"input_tokens":544,"output_tokens_details":{"text_tokens":588},"image_tokens":520},"request_id":"758b0356-653b-98ac-b4d3-f812437ba1ec"}
    
    id:567
    event:result
    :HTTP_STATUS/200
    data:{"output":{"choices":[{"message":{"content":[{"text":"centimeters"}],"role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":1133,"input_tokens_details":{"image_tokens":520,"text_tokens":24},"output_tokens":589,"input_tokens":544,"output_tokens_details":{"text_tokens":589},"image_tokens":520},"request_id":"758b0356-653b-98ac-b4d3-f812437ba1ec"}
    
    id:568
    event:result
    :HTTP_STATUS/200
    data:{"output":{"choices":[{"message":{"content":[],"role":"assistant"},"finish_reason":"stop"}]},"usage":{"total_tokens":1134,"input_tokens_details":{"image_tokens":520,"text_tokens":24},"output_tokens":590,"input_tokens":544,"output_tokens_details":{"text_tokens":590},"image_tokens":520},"request_id":"758b0356-653b-98ac-b4d3-f812437ba1ec"}

    Kemampuan inti

    Aktifkan atau nonaktifkan proses pemikiran

    Untuk skenario yang memerlukan penalaran detail, seperti pemecahan masalah atau analisis laporan, Anda dapat mengaktifkan mode pemikiran menggunakan parameter enable_thinking. Contoh berikut menunjukkan cara mengaktifkan pemikiran.

    Penting

    Parameter enable_thinking didukung oleh seri qwen3.5-plus, qwen3-vl-plus, qwen3-vl-flash, dan kimi-k2.5. Seri qwen3.5-plus secara default mengaktifkan pemikiran, di mana enable_thinking diatur ke true.

    Kompatibel dengan OpenAI

    Parameter enable_thinking dan thinking_budget merupakan parameter non-standar OpenAI. Metode pengirimannya berbeda tergantung bahasa SDK:

    • Python SDK: Anda dapat mengirimkannya melalui dictionary extra_body.

    • Node.js SDK: Anda dapat mengirimkannya langsung sebagai parameter tingkat atas.

    import os
    from openai import OpenAI
    
    client = OpenAI(
        # Kunci API berbeda-beda berdasarkan wilayah. Dapatkan kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/compatible-mode/v1
        # Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/compatible-mode/v1
        base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    )
    
    reasoning_content = ""  # Definisikan proses berpikir lengkap
    answer_content = ""     # Definisikan tanggapan lengkap
    is_answering = False   # Periksa apakah proses berpikir telah berakhir dan tanggapan telah dimulai
    enable_thinking = True
    # Buat permintaan penyelesaian obrolan
    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": "Bagaimana cara menyelesaikan masalah ini?"},
                ],
            },
        ],
        stream=True,
        # Parameter enable_thinking mengaktifkan proses berpikir. Parameter thinking_budget menetapkan jumlah maksimum token untuk proses penalaran.
        # Untuk qwen3.5-plus, qwen3-vl-plus, dan qwen3-vl-flash, Anda dapat menggunakan enable_thinking untuk mengaktifkan atau menonaktifkan proses berpikir (qwen3.5-plus diaktifkan secara default). Untuk model dengan akhiran 'thinking', seperti qwen3-vl-235b-a22b-thinking, enable_thinking hanya dapat diatur ke true. Parameter ini tidak berlaku untuk model Qwen-VL lainnya.
        extra_body={
            'enable_thinking': enable_thinking
            },
    
        # Batalkan komentar berikut untuk mengembalikan penggunaan token dalam chunk terakhir
        # stream_options={
        #     "include_usage": True
        # }
    )
    
    if enable_thinking:
        print("\n" + "=" * 20 + "Proses berpikir" + "=" * 20 + "\n")
    
    for chunk in completion:
        # Jika chunk.choices kosong, cetak penggunaan
        if not chunk.choices:
            print("\nPenggunaan:")
            print(chunk.usage)
        else:
            delta = chunk.choices[0].delta
            # Cetak proses berpikir
            if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
                print(delta.reasoning_content, end='', flush=True)
                reasoning_content += delta.reasoning_content
            else:
                # Mulai memberikan tanggapan
                if delta.content != "" and is_answering is False:
                    print("\n" + "=" * 20 + "Tanggapan lengkap" + "=" * 20 + "\n")
                    is_answering = True
                # Cetak proses tanggapan
                print(delta.content, end='', flush=True)
                answer_content += delta.content
    
    # print("=" * 20 + "Proses berpikir lengkap" + "=" * 20 + "\n")
    # print(reasoning_content)
    # print("=" * 20 + "Tanggapan lengkap" + "=" * 20 + "\n")
    # print(answer_content)
    import OpenAI from "openai";
    
    // Inisialisasi klien OpenAI
    const openai = new OpenAI({
      // API key berbeda tiap wilayah. Dapatkan Kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
      // Jika Anda belum mengonfigurasi variabel lingkungan, ganti baris berikut dengan Kunci API Model Studio Anda: apiKey: "sk-xxx"
      apiKey: process.env.DASHSCOPE_API_KEY,
     // URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/compatible-mode/v1
     //  Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/compatible-mode/v1
      baseURL: "https://dashscope-intl.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,
              // Catatan: Di Node.js SDK, parameter non-standar seperti enableThinking dikirim sebagai properti tingkat atas, bukan di 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;
    
                // Tangani proses pemikiran
                if (delta.reasoning_content) {
                    process.stdout.write(delta.reasoning_content);
                    reasoningContent += delta.reasoning_content;
                }
                // Tangani respons formal
                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 =======
    # URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/compatible-mode/v1/chat/completions
    # Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
    # API key berbeda tiap wilayah. Dapatkan Kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    # === Hapus komentar ini sebelum eksekusi ===
    
    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": "qwen3.5-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
    }'

    DashScope

    import os
    import dashscope
    from dashscope import MultiModalConversation
    
    // URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/api/v1
    // Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/api/v1
    dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1"
    
    enable_thinking = True
    
    messages = [
        {
            "role": "user",
            "content": [
                {"image": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"},
                {"text": "How do I solve this problem?"}
            ]
        }
    ]
    
    response = MultiModalConversation.call(
        // Jika Anda belum mengonfigurasi variabel lingkungan, ganti baris berikut dengan Kunci API Model Studio Anda: api_key="sk-xxx",
        // API key berbeda tiap wilayah. Dapatkan Kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
        api_key=os.getenv('DASHSCOPE_API_KEY'),
        model="qwen3.5-plus",  
        messages=messages,
        stream=True,
        // Parameter enable_thinking mengaktifkan proses pemikiran.
        // Untuk qwen3.5-plus, qwen3-vl-plus, dan qwen3-vl-flash, Anda dapat menggunakan enable_thinking untuk mengaktifkan atau menonaktifkan pemikiran (qwen3.5-plus diaktifkan secara default). Untuk model dengan akhiran 'thinking', seperti qwen3-vl-235b-a22b-thinking, enable_thinking hanya dapat diatur ke true. Parameter ini tidak berlaku untuk model Qwen-VL lainnya.
        enable_thinking=enable_thinking
    
    )
    
    // Definisikan proses pemikiran lengkap
    reasoning_content = ""
    // Definisikan respons lengkap
    answer_content = ""
    // Periksa apakah proses pemikiran telah berakhir dan respons telah dimulai
    is_answering = False
    
    if enable_thinking:
        print("=" * 20 + "Thinking process" + "=" * 20)
    
    for chunk in response:
        // Jika proses pemikiran dan respons keduanya kosong, abaikan
        message = chunk.output.choices[0].message
        reasoning_content_chunk = message.get("reasoning_content", None)
        if (chunk.output.choices[0].message.content == [] and
            reasoning_content_chunk == ""):
            pass
        else:
            // Jika sedang dalam proses pemikiran
            if reasoning_content_chunk != None and chunk.output.choices[0].message.content == []:
                print(chunk.output.choices[0].message.reasoning_content, end="")
                reasoning_content += chunk.output.choices[0].message.reasoning_content
            // Jika sedang dalam respons
            elif chunk.output.choices[0].message.content != []:
                if not is_answering:
                    print("\n" + "=" * 20 + "Full response" + "=" * 20)
                    is_answering = True
                print(chunk.output.choices[0].message.content[0]["text"], end="")
                answer_content += chunk.output.choices[0].message.content[0]["text"]
    
    // Untuk mencetak proses pemikiran dan respons lengkap, hapus komentar dan jalankan kode berikut
    // print("=" * 20 + "Full thinking process" + "=" * 20 + "\n")
    // print(f"{reasoning_content}")
    // print("=" * 20 + "Full response" + "=" * 20 + "\n")
    // print(f"{answer_content}")
    // DashScope SDK version >= 2.21.10
    import java.util.*;
    
    import org.slf4j.Logger;
    import org.slf4j.LoggerFactory;
    
    import com.alibaba.dashscope.common.Role;
    import com.alibaba.dashscope.exception.ApiException;
    import com.alibaba.dashscope.exception.NoApiKeyException;
    import io.reactivex.Flowable;
    
    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.exception.UploadFileException;
    import com.alibaba.dashscope.exception.InputRequiredException;
    import java.lang.System;
    import com.alibaba.dashscope.utils.Constants;
    
    public class Main {
        // URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/api/v1
        // Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/api/v1
        static {Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";}
    
        private static final Logger logger = LoggerFactory.getLogger(Main.class);
        private static StringBuilder reasoningContent = new StringBuilder();
        private static StringBuilder finalContent = new StringBuilder();
        private static boolean isFirstPrint = true;
    
        private static void handleGenerationResult(MultiModalConversationResult message) {
            String re = message.getOutput().getChoices().get(0).getMessage().getReasoningContent();
            String reasoning = Objects.isNull(re)?"":re; // Default value
    
            List<Map<String, Object>> content = message.getOutput().getChoices().get(0).getMessage().getContent();
            if (!reasoning.isEmpty()) {
                reasoningContent.append(reasoning);
                if (isFirstPrint) {
                    System.out.println("====================Thinking process====================");
                    isFirstPrint = false;
                }
                System.out.print(reasoning);
            }
    
            if (Objects.nonNull(content) && !content.isEmpty()) {
                Object text = content.get(0).get("text");
                finalContent.append(content.get(0).get("text"));
                if (!isFirstPrint) {
                    System.out.println("\n====================Full response====================");
                    isFirstPrint = true;
                }
                System.out.print(text);
            }
        }
        public static MultiModalConversationParam buildMultiModalConversationParam(MultiModalMessage Msg)  {
            return MultiModalConversationParam.builder()
                    // Jika Anda belum mengonfigurasi variabel lingkungan, ganti baris berikut dengan Kunci API Model Studio Anda: .apiKey("sk-xxx")
                    // API key berbeda tiap wilayah. Dapatkan Kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
                    .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                    .model("qwen3.5-plus")
                    .messages(Arrays.asList(Msg))
                    .enableThinking(true)
                    .incrementalOutput(true)
                    .build();
        }
    
        public static void streamCallWithMessage(MultiModalConversation conv, MultiModalMessage Msg)
                throws NoApiKeyException, ApiException, InputRequiredException, UploadFileException {
            MultiModalConversationParam param = buildMultiModalConversationParam(Msg);
            Flowable<MultiModalConversationResult> result = conv.streamCall(param);
            result.blockingForEach(message -> {
                handleGenerationResult(message);
            });
        }
        public static void main(String[] args) {
            try {
                MultiModalConversation conv = new MultiModalConversation();
                MultiModalMessage userMsg = MultiModalMessage.builder()
                        .role(Role.USER.getValue())
                        .content(Arrays.asList(Collections.singletonMap("image", "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"),
                                Collections.singletonMap("text", "Solve this problem")))
                        .build();
                streamCallWithMessage(conv, userMsg);
    //             Cetak hasil akhir
    //            if (reasoningContent.length() > 0) {
    //                System.out.println("\n====================Full response====================");
    //                System.out.println(finalContent.toString());
    //            }
            } catch (ApiException | NoApiKeyException | UploadFileException | InputRequiredException e) {
                logger.error("An exception occurred: {}", e.getMessage());
            }
            System.exit(0);
        }
    }
    # ======= IMPORTANT =======
    // API key berbeda tiap wilayah. Dapatkan Kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    // URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
    // Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
    // === Hapus komentar ini sebelum eksekusi ===
    
    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' \
    -H 'X-DashScope-SSE: enable' \
    -d '{
        "model": "qwen3.5-plus",
        "input":{
            "messages":[
                {
                    "role": "user",
                    "content": [
                        {"image": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"},
                        {"text": "Solve this problem"}
                    ]
                }
            ]
        },
        "parameters":{
            "enable_thinking": true,
            "incremental_output": true
        }
    }'

    Batasi panjang pemikiran

    Untuk mencegah model penalaran visual menghasilkan proses penalaran yang terlalu panjang, Anda dapat menggunakan parameter thinking_budget untuk membatasi jumlah maksimum token yang dihasilkan dalam proses penalaran. Ketika proses penalaran melebihi batas ini, kontennya dipotong dan model segera mulai menghasilkan jawaban akhir. Nilai default thinking_budget adalah panjang maksimum rantai-pikiran model. Untuk informasi lebih lanjut, lihat Daftar Model.

    Penting

    Parameter thinking_budget didukung oleh Qwen3-VL (mode penalaran) dan kimi-k2.5 (mode penalaran).

    Kompatibel dengan OpenAI

    Parameter thinking_budget merupakan parameter non-standar OpenAI. Saat Anda menggunakan OpenAI Python SDK, Anda dapat mengirimkannya melalui dictionary extra_body.

    import os
    from openai import OpenAI
    
    client = OpenAI(
        // API key berbeda tiap wilayah. Dapatkan Kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        // URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/compatible-mode/v1
        // Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/compatible-mode/v1
        base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    )
    
    reasoning_content = ""  // Definisikan proses pemikiran lengkap
    answer_content = ""     // Definisikan respons lengkap
    is_answering = False   // Periksa apakah proses pemikiran telah berakhir dan respons telah dimulai
    enable_thinking = True
    // Buat permintaan chat completion
    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,
        // Parameter enable_thinking mengaktifkan proses pemikiran. Parameter thinking_budget mengatur jumlah maksimum token untuk proses penalaran.
        // Untuk qwen3.5-plus, qwen3-vl-plus, dan qwen3-vl-flash, Anda dapat menggunakan enable_thinking untuk mengaktifkan atau menonaktifkan pemikiran (qwen3.5-plus diaktifkan secara default). Untuk model dengan akhiran 'thinking', seperti qwen3-vl-235b-a22b-thinking, enable_thinking hanya dapat diatur ke true. Parameter ini tidak berlaku untuk model Qwen-VL lainnya.
        extra_body={
            'enable_thinking': enable_thinking,
            "thinking_budget": 81920},
    
        // Hapus komentar berikut untuk mengembalikan penggunaan token pada chunk terakhir
        // stream_options={
        //     "include_usage": True
        // }
    )
    
    if enable_thinking:
        print("\n" + "=" * 20 + "Thinking process" + "=" * 20 + "\n")
    
    for chunk in completion:
        // Jika chunk.choices kosong, cetak penggunaan
        if not chunk.choices:
            print("\nUsage:")
            print(chunk.usage)
        else:
            delta = chunk.choices[0].delta
            // Cetak proses pemikiran
            if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
                print(delta.reasoning_content, end='', flush=True)
                reasoning_content += delta.reasoning_content
            else:
                // Mulai merespons
                if delta.content != "" and is_answering is False:
                    print("\n" + "=" * 20 + "Full response" + "=" * 20 + "\n")
                    is_answering = True
                // Cetak proses respons
                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";
    
    // Inisialisasi klien OpenAI
    const openai = new OpenAI({
      // API key berbeda tiap wilayah. Dapatkan Kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
      // Jika Anda belum mengonfigurasi variabel lingkungan, ganti baris berikut dengan Kunci API Model Studio Anda: apiKey: "sk-xxx"
      apiKey: process.env.DASHSCOPE_API_KEY,
      // URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/compatible-mode/v1
      // Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/compatible-mode/v1
      baseURL: "https://dashscope-intl.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,
              // Catatan: Di Node.js SDK, parameter non-standar seperti enableThinking dikirim sebagai properti tingkat atas, bukan di 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;
    
                // Tangani proses pemikiran
                if (delta.reasoning_content) {
                    process.stdout.write(delta.reasoning_content);
                    reasoningContent += delta.reasoning_content;
                }
                // Tangani respons formal
                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 =======
    // URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/compatible-mode/v1/chat/completions
    // Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
    // API key berbeda tiap wilayah. Dapatkan Kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    // === Hapus komentar ini sebelum eksekusi ===
    
    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": "qwen3.5-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
    }'

    DashScope

    import os
    import dashscope
    from dashscope import MultiModalConversation
    
    # URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/api/v1
    # Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/api/v1
    dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1"
    
    enable_thinking = True
    
    messages = [
        {
            "role": "user",
            "content": [
                {"image": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"},
                {"text": "How do I solve this problem?"}
            ]
        }
    ]
    
    response = MultiModalConversation.call(
        # Jika Anda belum mengonfigurasi variabel lingkungan, ganti baris berikut dengan kunci API Model Studio Anda: api_key="sk-xxx",
        # Kunci API berbeda menurut Wilayah. Dapatkan kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
        api_key=os.getenv('DASHSCOPE_API_KEY'),
        model="qwen3.5-plus",  
        messages=messages,
        stream=True,
        # Parameter enable_thinking mengaktifkan proses berpikir.
        # Untuk qwen3.5-plus, qwen3-vl-plus, dan qwen3-vl-flash, Anda dapat menggunakan enable_thinking untuk mengaktifkan atau menonaktifkan proses berpikir (qwen3.5-plus diaktifkan secara default). Untuk model dengan akhiran 'thinking', seperti qwen3-vl-235b-a22b-thinking, enable_thinking hanya dapat diatur ke true. Parameter ini tidak berlaku untuk model Qwen-VL lainnya.
        enable_thinking=enable_thinking,
        # Parameter thinking_budget menetapkan jumlah token maksimum untuk proses penalaran.
        thinking_budget=81920,
    
    )
    
    # Tentukan proses berpikir lengkap
    reasoning_content = ""
    # Tentukan tanggapan lengkap
    answer_content = ""
    # Periksa apakah proses berpikir telah berakhir dan tanggapan telah dimulai
    is_answering = False
    
    if enable_thinking:
        print("=" * 20 + "Thinking process" + "=" * 20)
    
    for chunk in response:
        # Jika proses berpikir dan tanggapan keduanya kosong, abaikan
        message = chunk.output.choices[0].message
        reasoning_content_chunk = message.get("reasoning_content", None)
        if (chunk.output.choices[0].message.content == [] and
            reasoning_content_chunk == ""):
            pass
        else:
            # Jika saat ini adalah proses berpikir
            if reasoning_content_chunk != None and chunk.output.choices[0].message.content == []:
                print(chunk.output.choices[0].message.reasoning_content, end="")
                reasoning_content += chunk.output.choices[0].message.reasoning_content
            # Jika saat ini adalah tanggapan
            elif chunk.output.choices[0].message.content != []:
                if not is_answering:
                    print("\n" + "=" * 20 + "Full response" + "=" * 20)
                    is_answering = True
                print(chunk.output.choices[0].message.content[0]["text"], end="")
                answer_content += chunk.output.choices[0].message.content[0]["text"]
    
    # Untuk mencetak proses berpikir dan tanggapan lengkap, hapus tanda komentar dan jalankan kode berikut
    # print("=" * 20 + "Full thinking process" + "=" * 20 + "\n")
    # print(f"{reasoning_content}")
    # print("=" * 20 + "Full response" + "=" * 20 + "\n")
    # print(f"{answer_content}")
    // DashScope SDK version >= 2.21.10
    import java.util.*;
    
    import org.slf4j.Logger;
    import org.slf4j.LoggerFactory;
    
    import com.alibaba.dashscope.common.Role;
    import com.alibaba.dashscope.exception.ApiException;
    import com.alibaba.dashscope.exception.NoApiKeyException;
    import io.reactivex.Flowable;
    
    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.exception.UploadFileException;
    import com.alibaba.dashscope.exception.InputRequiredException;
    import java.lang.System;
    import com.alibaba.dashscope.utils.Constants;
    
    public class Main {
        // URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/api/v1
        // Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/api/v1
        static {Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";}
    
        private static final Logger logger = LoggerFactory.getLogger(Main.class);
        private static StringBuilder reasoningContent = new StringBuilder();
        private static StringBuilder finalContent = new StringBuilder();
        private static boolean isFirstPrint = true;
    
        private static void handleGenerationResult(MultiModalConversationResult message) {
            String re = message.getOutput().getChoices().get(0).getMessage().getReasoningContent();
            String reasoning = Objects.isNull(re)?"":re; // Default value
    
            List<Map<String, Object>> content = message.getOutput().getChoices().get(0).getMessage().getContent();
            if (!reasoning.isEmpty()) {
                reasoningContent.append(reasoning);
                if (isFirstPrint) {
                    System.out.println("====================Thinking process====================");
                    isFirstPrint = false;
                }
                System.out.print(reasoning);
            }
    
            if (Objects.nonNull(content) && !content.isEmpty()) {
                Object text = content.get(0).get("text");
                finalContent.append(content.get(0).get("text"));
                if (!isFirstPrint) {
                    System.out.println("\n====================Full response====================");
                    isFirstPrint = true;
                }
                System.out.print(text);
            }
        }
        public static MultiModalConversationParam buildMultiModalConversationParam(MultiModalMessage Msg)  {
            return MultiModalConversationParam.builder()
                    // Jika Anda belum mengonfigurasi variabel lingkungan, ganti baris berikut dengan Kunci API Model Studio Anda: .apiKey("sk-xxx")
                    // API key berbeda tiap wilayah. Dapatkan Kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
                    .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                    .model("qwen3.5-plus")
                    .messages(Arrays.asList(Msg))
                    .enableThinking(true)
                    .thinkingBudget(81920)
                    .incrementalOutput(true)
                    .build();
        }
    
        public static void streamCallWithMessage(MultiModalConversation conv, MultiModalMessage Msg)
                throws NoApiKeyException, ApiException, InputRequiredException, UploadFileException {
            MultiModalConversationParam param = buildMultiModalConversationParam(Msg);
            Flowable<MultiModalConversationResult> result = conv.streamCall(param);
            result.blockingForEach(message -> {
                handleGenerationResult(message);
            });
        }
        public static void main(String[] args) {
            try {
                MultiModalConversation conv = new MultiModalConversation();
                MultiModalMessage userMsg = MultiModalMessage.builder()
                        .role(Role.USER.getValue())
                        .content(Arrays.asList(Collections.singletonMap("image", "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"),
                                Collections.singletonMap("text", "Solve this problem")))
                        .build();
                streamCallWithMessage(conv, userMsg);
    //             Cetak hasil akhir
    //            if (reasoningContent.length() > 0) {
    //                System.out.println("\n====================Full response====================");
    //                System.out.println(finalContent.toString());
    //            }
            } catch (ApiException | NoApiKeyException | UploadFileException | InputRequiredException e) {
                logger.error("An exception occurred: {}", e.getMessage());
            }
            System.exit(0);
        }
    }
    # ======= IMPORTANT =======
    // API key berbeda tiap wilayah. Dapatkan Kunci API di https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    // URL dasar Singapura. Untuk model AS (Virginia), gunakan https://dashscope-us.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
    // Untuk model Beijing, gunakan https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
    // === Hapus komentar ini sebelum eksekusi ===
    
    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' \
    -H 'X-DashScope-SSE: enable' \
    -d '{
        "model": "qwen3.5-plus",
        "input":{
            "messages":[
                {
                    "role": "user",
                    "content": [
                        {"image": "https://img.alicdn.com/imgextra/i1/O1CN01gDEY8M1W114Hi3XcN_!!6000000002727-0-tps-1024-406.jpg"},
                        {"text": "Solve this problem"}
                    ]
                }
            ]
        },
        "parameters":{
            "enable_thinking": true,
            "incremental_output": true,
            "thinking_budget": 81920
        }
    }'

    Contoh lainnya

    Selain kemampuan berpikir, model penalaran visual mendukung semua fitur pemahaman visual untuk skenario kompleks seperti:

    • Pemahaman multi-gambar

    • Pemahaman video

    • Pemrosesan gambar resolusi tinggi

    • Mengirim file lokal (encoding Base64 atau path file)

    Penagihan

    Total biaya = (Token input × Harga per token input) + (Token output × Harga per token output).

    • Proses pemikiran (reasoning_content) ditagih sebagai bagian dari token output. Jika model tidak menghasilkan proses pemikiran dalam mode berpikir, maka akan ditagih dengan tarif mode non-berpikir.

    • Untuk metode perhitungan token gambar atau video, lihat Pemahaman gambar dan video.

    Referensi API

    Untuk informasi lebih lanjut tentang parameter input dan output model penalaran visual, lihat Qwen.

    Kode error

    Jika pemanggilan model gagal dan mengembalikan pesan error, lihat Pesan error untuk penyelesaian.

    Thank you! We've received your feedback.