Referensi API Qwen-OCR - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center

Ekstrak teks, data terstruktur, dan informasi penting dari gambar menggunakan model Qwen-OCR. Qwen-OCR mendukung dua protokol API: API kompatibel OpenAI dan API DashScope .

Untuk kasus penggunaan dan panduan memulai, lihat Ekstraksi teks (Qwen-OCR).

API kompatibel OpenAI

Titik akhir

Wilayah	SDK`base_url`	Titik akhir HTTP
Singapore	`https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1`	`POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions`
US (Virginia)	`https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1`	`POST https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions`
China (Beijing)	`https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1`	`POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions`

PentingAlibaba Cloud Model Studio telah merilis domain khusus ruang kerja untuk wilayah China (Beijing) dan Singapura. Domain khusus baru ini memberikan performa lebih unggul dan stabilitas lebih tinggi untuk permintaan inferensi. Kami merekomendasikan migrasi ke domain baru:

China (Beijing): dari https://dashscope.aliyuncs.com ke https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com
Singapura: dari https://dashscope-intl.aliyuncs.com ke https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com

{WorkspaceId} adalah ID ruang kerja Anda, yang dapat ditemukan di halaman Detail Ruang Kerja di Konsol Alibaba Cloud Model Studio. Domain lama tetap berfungsi sepenuhnya.

Prasyarat

Dapatkan Kunci API dan tetapkan sebagai variabel lingkungan. Jika Anda menggunakan SDK OpenAI, instal SDK tersebut.

Panduan cepat

Gunakan titik akhir chat completions yang kompatibel OpenAI. Kirim pesan user dengan URL gambar dan prompt teks. Model mengekstrak teks dan mengembalikannya dalam choices[0].message.content.

Tidak streaming

Python

from openai import OpenAI
import os

PROMPT_TICKET_EXTRACTION = """
Please extract the invoice number, train number, departure station, arrival station, departure date and time, seat number, seat class, ticket price, ID card number, and passenger name from the train ticket image.
You must accurately extract the key information. Do not omit or fabricate information. Replace any single character that is blurry or obscured by strong light with an English question mark (?).
Return the data in JSON format as follows: {'invoice_number': 'xxx', 'departure_station': 'xxx', 'arrival_station': 'xxx', 'departure_date_and_time':'xxx', 'seat_number': 'xxx','ticket_price':'xxx', 'id_card_number': 'xxx', 'passenger_name': 'xxx'},
"""

try:
    client = OpenAI(
        # If the environment variable is not configured, replace with: api_key="sk-xxx"
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # Singapore region. For US (Virginia), use https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1
        # For China (Beijing), use https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
        base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
    )
    completion = client.chat.completions.create(
        model="qwen-vl-ocr-2025-11-20",
        messages=[
            {
                "role": "user",
                "content": [
                    {
                        "type": "image_url",
                        "image_url": {"url":"https://img.alicdn.com/imgextra/i2/O1CN01ktT8451iQutqReELT_!!6000000004408-0-tps-689-487.jpg"},
                        # Minimum pixel count. Images below this are upscaled.
                        "min_pixels": 32 * 32 * 3,
                        # Maximum pixel count. Images above this are downscaled.
                        "max_pixels": 32 * 32 * 8192
                    },
                    # Custom prompt. Without this, the model uses: "Please output only the text content from the image without any additional descriptions or formatting."
                    {"type": "text",
                     "text": PROMPT_TICKET_EXTRACTION}
                ]
            }
        ])
    print(completion.choices[0].message.content)
except Exception as e:
    print(f"Error message: {e}")

Node.js

import OpenAI from 'openai';

const PROMPT_TICKET_EXTRACTION = `
Please extract the invoice number, train number, departure station, arrival station, departure date and time, seat number, seat class, ticket price, ID card number, and passenger name from the train ticket image.
You must accurately extract the key information. Do not omit or fabricate information. Replace any single character that is blurry or obscured by strong light with an English question mark (?).
Return the data in JSON format as follows: {'invoice_number': 'xxx', 'departure_station': 'xxx', 'arrival_station': 'xxx', 'departure_date_and_time':'xxx', 'seat_number': 'xxx','ticket_price':'xxx', 'id_card_number': 'xxx', 'passenger_name': 'xxx'}
`;

const client = new OpenAI({
  // If the environment variable is not configured, replace with: apiKey: "sk-xxx"
  apiKey: process.env.DASHSCOPE_API_KEY,
  // For China (Beijing), use https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
  baseURL: 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1',
});

async function main() {
  const response = await client.chat.completions.create({
    model: 'qwen-vl-ocr-2025-11-20',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: PROMPT_TICKET_EXTRACTION},
          {
            type: 'image_url',
            image_url: {
              url: 'https://img.alicdn.com/imgextra/i2/O1CN01ktT8451iQutqReELT_!!6000000004408-0-tps-689-487.jpg',
            },
              // Minimum pixel count. Images below this are upscaled.
              "min_pixels": 32 * 32 * 3,
              // Maximum pixel count. Images above this are downscaled.
              "max_pixels": 32 * 32 * 8192
          }
        ]
      }
    ],
  });
  console.log(response.choices[0].message.content)
}

main();

curl

curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "qwen-vl-ocr-2025-11-20",
  "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {"url":"https://img.alicdn.com/imgextra/i2/O1CN01ktT8451iQutqReELT_!!6000000004408-0-tps-689-487.jpg"},
                    "min_pixels": 3072,
                    "max_pixels": 8388608
                },
                {"type": "text", "text": "Please extract the invoice number, train number, departure station, arrival station, departure date and time, seat number, seat class, ticket price, ID card number, and passenger name from the train ticket image. You must accurately extract the key information. Do not omit or fabricate information. Replace any single character that is blurry or obscured by strong light with an English question mark (?). Return the data in JSON format as follows: {\'invoice_number\': \'xxx\', \'departure_station\': \'xxx\', \'arrival_station\': \'xxx\', \'departure_date_and_time\':\'xxx\', \'seat_number\': \'xxx\',\'ticket_price\':\'xxx\', \'id_card_number\': \'xxx\', \'passenger_name\': \'xxx\'}"}
            ]
        }
    ]
}'

Streaming

Atur stream ke true untuk menerima hasil secara bertahap saat model menghasilkannya.

Python

import os
from openai import OpenAI

PROMPT_TICKET_EXTRACTION = """
Please extract the invoice number, train number, departure station, arrival station, departure date and time, seat number, seat class, ticket price, ID card number, and passenger name from the train ticket image.
You must accurately extract the key information. Do not omit or fabricate information. Replace any single character that is blurry or obscured by strong light with an English question mark (?).
Return the data in JSON format as follows: {'invoice_number': 'xxx','departure_station': 'xxx', 'arrival_station': 'xxx', 'departure_date_and_time':'xxx', 'seat_number': 'xxx','ticket_price':'xxx', 'id_card_number': 'xxx', 'passenger_name': 'xxx'},
"""

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
    model="qwen-vl-ocr-2025-11-20",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {"url":"https://img.alicdn.com/imgextra/i2/O1CN01ktT8451iQutqReELT_!!6000000004408-0-tps-689-487.jpg"},
                    "min_pixels": 32 * 32 * 3,
                    "max_pixels": 32 * 32 * 8192
                },
                {"type": "text","text": PROMPT_TICKET_EXTRACTION}
            ]
        }
    ],
    stream=True,
    stream_options={"include_usage": True}
)

for chunk in completion:
    print(chunk.model_dump_json())

Node.js

import OpenAI from 'openai';

const PROMPT_TICKET_EXTRACTION = `
Please extract the invoice number, train number, departure station, arrival station, departure date and time, seat number, seat class, ticket price, ID card number, and passenger name from the train ticket image.
You must accurately extract the key information. Do not omit or fabricate information. Replace any single character that is blurry or obscured by strong light with an English question mark (?).
Return the data in JSON format as follows: {'invoice_number': 'xxx', 'departure_station': 'xxx', 'arrival_station': 'xxx', 'departure_date_and_time':'xxx', 'seat_number': 'xxx','ticket_price':'xxx', 'id_card_number': 'xxx', 'passenger_name': 'xxx'}
`;

const openai = new OpenAI({
  apiKey: process.env.DASHSCOPE_API_KEY,
  baseURL: 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1',
});

async function main() {
  const response = await openai.chat.completions.create({
    model: 'qwen-vl-ocr-2025-11-20',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: PROMPT_TICKET_EXTRACTION},
          {
            type: 'image_url',
            image_url: {
              url: 'https://img.alicdn.com/imgextra/i2/O1CN01ktT8451iQutqReELT_!!6000000004408-0-tps-689-487.jpg',
            },
              "min_pixels": 32 * 32 * 3,
              "max_pixels": 32 * 32 * 8192
          }
        ]
      }
    ],
    stream: true,
    stream_options:{"include_usage": true}
  });
  let fullContent = ""
  console.log("Streaming output content:")
  for await (const chunk of response) {
    if (chunk.choices[0] && chunk.choices[0].delta.content != null) {
      fullContent += chunk.choices[0].delta.content;
      console.log(chunk.choices[0].delta.content);
    }
  }
  console.log(`Full output content: ${fullContent}`)
}

main();

curl

curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "qwen-vl-ocr-2025-11-20",
  "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {"url":"https://img.alicdn.com/imgextra/i2/O1CN01ktT8451iQutqReELT_!!6000000004408-0-tps-689-487.jpg"},
                    "min_pixels": 3072,
                    "max_pixels": 8388608
                },
                {"type": "text", "text": "Please extract the invoice number, train number, departure station, arrival station, departure date and time, seat number, seat class, ticket price, ID card number, and passenger name from the train ticket image. You must accurately extract the key information. Do not omit or fabricate information. Replace any single character that is blurry or obscured by strong light with an English question mark (?). Return the data in JSON format as follows: {\'invoice_number\': \'xxx\', \'departure_station\': \'xxx\', \'arrival_station\': \'xxx\', \'departure_date_and_time\':\'xxx\', \'seat_number\': \'xxx\',\'ticket_price\':\'xxx\', \'id_card_number\': \'xxx\', \'passenger_name\': \'xxx\'}"}
            ]
        }
    ],
    "stream": true,
    "stream_options": {"include_usage": true}
}'

Parameter permintaan

Parameter	Tipe	Wajib	Deskripsi
`model`	string	Ya	Nama model. Lihat Model yang direkomendasikan untuk daftar model yang didukung.
`messages`	array	Ya	Array objek pesan yang menyediakan konteks bagi model.

Objek pesan

Setiap pesan memerlukan role (harus user) dan array content dengan tipe elemen berikut:

Parameter	Tipe	Wajib	Deskripsi
`type`	string	Ya	`text` untuk input teks, `image_url` untuk input gambar.
`text`	string	Tidak	Prompt teks. Default: `"Please output only the text content from the image without any additional descriptions or formatting"`.
`image_url.url`	string	Ya (ketika `type` adalah `image_url`)	URL atau Data URL Base64 dari gambar. Untuk file lokal, lihat Ekstraksi teks.
`min_pixels`	integer	Tidak	Ambang batas piksel minimum. Gambar di bawah nilai ini diperbesar. Lihat Kontrol resolusi gambar.
`max_pixels`	integer	Tidak	Ambang batas piksel maksimum. Gambar di atas nilai ini diperkecil. Lihat Kontrol resolusi gambar.

Parameter generasi

Parameter	Type	Default	Deskripsi
`stream`	boolean	`false`	Atur ke `true` untuk menerima respons bertahap saat model menghasilkan output.
`stream_options.include_usage`	boolean	`false`	Ketika `stream` adalah `true`, atur ini ke `true` untuk menyertakan penggunaan token pada chunk terakhir.
`max_tokens`	integer	Bervariasi	Maksimum token dalam output. Melebihi batas ini akan memotong respons. Lihat Batas token output.
`temperature`	float	`0.01`	Mengatur keragaman output. Nilai lebih tinggi menghasilkan teks lebih bervariasi. Rentang: [0, 2).
`top_p`	float	`0.001`	Ambang batas sampling nucleus. Nilai lebih tinggi meningkatkan keragaman. Rentang: (0, 1.0]. Atur salah satu `temperature` atau `top_p`, bukan keduanya.
`top_k`	integer	`1`	Membatasi set token kandidat selama sampling. Jika nilainya None atau lebih besar dari 100, kebijakan top_k tidak diaktifkan, dan hanya kebijakan top_p yang berlaku. Harus >= 0. Bukan parameter standar OpenAI -- lewatkan melalui `extra_body` di SDK Python: `extra_body={"top_k": xxx}`. Di SDK Node.js atau HTTP, lewatkan di level teratas.
`repetition_penalty`	float	`1.0`	Hukuman untuk urutan berulang. Nilai di atas 1.0 mengurangi pengulangan. Bukan parameter standar OpenAI -- lewatkan melalui `extra_body` di SDK Python.
`presence_penalty`	float	`0.0`	Mengatur pengulangan konten. Rentang: [-2.0, 2.0]. Nilai positif mengurangi pengulangan.
`seed`	integer	--	Menjamin hasil yang dapat direproduksi ketika nilai yang sama digunakan dengan parameter identik. Rentang: [0, 2^31 - 1].
`logprobs`	boolean	`false`	Atur ke `true` untuk mengembalikan probabilitas log dari token output.
`top_logprobs`	integer	`0`	Jumlah token paling mungkin yang dikembalikan per langkah. Rentang: [0, 5]. Hanya efektif ketika `logprobs` adalah `true`.
`stop`	string atau array	--	Kata atau ID token penghenti. Generasi berhenti ketika string tertentu atau `token_id` muncul. Jangan mencampur string dan `token_id` dalam array yang sama.

Tanggapan

Tanggapan tidak streaming (`chat.completion`)

{
  "id": "chatcmpl-ba21fa91-dcd6-4dad-90cc-6d49c3c39094",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "```json\n{\n    \"seller_name\": \"null\",\n    \"buyer_name\": \"Cai Yingshi\",\n    \"price_excluding_tax\": \"230769.23\",\n    \"organization_code\": \"null\",\n    \"invoice_code\": \"142011726001\"\n}\n```",
        "refusal": null,
        "role": "assistant",
        "annotations": null,
        "audio": null,
        "function_call": null,
        "tool_calls": null
      }
    }
  ],
  "created": 1763283287,
  "model": "qwen-vl-ocr-latest",
  "object": "chat.completion",
  "service_tier": null,
  "system_fingerprint": null,
  "usage": {
    "completion_tokens": 72,
    "prompt_tokens": 1185,
    "total_tokens": 1257,
    "completion_tokens_details": {
      "accepted_prediction_tokens": null,
      "audio_tokens": null,
      "reasoning_tokens": null,
      "rejected_prediction_tokens": null,
      "text_tokens": 72
    },
    "prompt_tokens_details": {
      "audio_tokens": null,
      "cached_tokens": null,
      "image_tokens": 1001,
      "text_tokens": 184
    }
  }
}

Bidang	Type	Deskripsi
`id`	string	Identifier unik permintaan.
`choices`	array	Konten yang dihasilkan model.
`choices[].finish_reason`	string	`stop` ketika generasi selesai normal, `length` ketika dipotong karena batas token.
`choices[].index`	integer	Posisi dalam array `choices`.
`choices[].message.content`	string	Teks atau output terstruktur yang diekstrak dari model.
`choices[].message.role`	string	Selalu `assistant`.
`choices[].message.refusal`	string	Selalu `null`.
`choices[].message.audio`	object	Selalu `null`.
`choices[].message.function_call`	object	Selalu `null`.
`choices[].message.tool_calls`	array	Selalu `null`.
`created`	integer	Stempel waktu UNIX permintaan.
`model`	string	Model yang digunakan.
`object`	string	Selalu `chat.completion`.
`service_tier`	string	Selalu `null`.
`system_fingerprint`	string	Selalu `null`.
`usage.completion_tokens`	integer	Jumlah token output.
`usage.prompt_tokens`	integer	Jumlah token input.
`usage.total_tokens`	integer	Jumlah dari `prompt_tokens` dan `completion_tokens`.
`usage.completion_tokens_details.text_tokens`	integer	Token output teks. Bidang lain dalam `completion_tokens_details` selalu `null`.
`usage.prompt_tokens_details.image_tokens`	integer	Token input gambar.
`usage.prompt_tokens_details.text_tokens`	integer	Token input teks. Bidang lain dalam `prompt_tokens_details` selalu `null`.

Tanggapan streaming (`chat.completion.chunk`)

Ketika stream adalah true, tanggapan dikirim sebagai rangkaian chunk Server-Sent Event (SSE). Setiap chunk mengikuti struktur yang sama dengan tanggapan tidak streaming, dengan perbedaan berikut:

object selalu chat.completion.chunk.
choices[].delta menggantikan choices[].message. Objek delta memiliki bidang yang sama dengan message.
choices[].delta.role hanya dikembalikan pada chunk pertama.
finish_reason adalah null selama generasi, stop saat selesai, atau length jika dipotong.
Ketika include_usage adalah true, chunk terakhir memiliki array choices kosong dan menyertakan objek usage.

{"id":"chatcmpl-f6fbdc0d-78d6-418f-856f-f099c2e4859b","choices":[{"delta":{"content":"","function_call":null,"refusal":null,"role":"assistant","tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1764139204,"model":"qwen-vl-ocr-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-f6fbdc0d-78d6-418f-856f-f099c2e4859b","choices":[{"delta":{"content":"```","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1764139204,"model":"qwen-vl-ocr-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-f6fbdc0d-78d6-418f-856f-f099c2e4859b","choices":[{"delta":{"content":"json","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1764139204,"model":"qwen-vl-ocr-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
......
{"id":"chatcmpl-f6fbdc0d-78d6-418f-856f-f099c2e4859b","choices":[{"delta":{"content":"","function_call":null,"refusal":null,"role":null,"tool_calls":null},"finish_reason":"stop","index":0,"logprobs":null}],"created":1764139204,"model":"qwen-vl-ocr-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":null}
{"id":"chatcmpl-f6fbdc0d-78d6-418f-856f-f099c2e4859b","choices":[],"created":1764139204,"model":"qwen-vl-ocr-latest","object":"chat.completion.chunk","service_tier":null,"system_fingerprint":null,"usage":{"completion_tokens":141,"prompt_tokens":513,"total_tokens":654,"completion_tokens_details":{"accepted_prediction_tokens":null,"audio_tokens":null,"reasoning_tokens":null,"rejected_prediction_tokens":null,"text_tokens":141},"prompt_tokens_details":{"audio_tokens":null,"cached_tokens":null,"image_tokens":332,"text_tokens":181}}}

Kontrol resolusi gambar

min_pixels dan max_pixels mengatur penskalaan ulang gambar sebelum pemrosesan. Rasio token-per-piksel bergantung pada versi model:

Model	Piksel per token	`min_pixels`default (minimum)	`max_pixels`default	`max_pixels`maksimum
`qwen3.5-ocr`, `qwen-vl-ocr-latest`, `qwen-vl-ocr-2025-11-20`	32 x 32 = 1.024	3.072 (3 token)	8.388.608 (8.192 token)	30.720.000 (30.000 token)
`qwen-vl-ocr`, `qwen-vl-ocr-2025-08-28`, dan sebelumnya	28 x 28 = 784	3.136 (4 token)	6.422.528 (8.192 token)	23.520.000 (30.000 token)

Perilaku penskalaan ulang:

Jika jumlah piksel gambar di bawah min_pixels, gambar diperbesar hingga melebihi min_pixels.
Jika jumlah piksel gambar berada dalam rentang [min_pixels, max_pixels], gambar asli digunakan tanpa penskalaan ulang.
Jika jumlah piksel gambar melebihi max_pixels, gambar diperkecil di bawah max_pixels.

Batas token output

Model	Default dan maksimum`max_tokens`
`qwen3.5-ocr`, `qwen-vl-ocr-latest`, `qwen-vl-ocr-2025-11-20`, `qwen-vl-ocr-2024-10-28`	Sama dengan panjang output maksimum model. Lihat Pemilihan model.
`qwen-vl-ocr`, `qwen-vl-ocr-2025-04-13`, `qwen-vl-ocr-2025-08-28`	4.096

Untuk qwen-vl-ocr, qwen-vl-ocr-2025-04-13, dan qwen-vl-ocr-2025-08-28, nilai default max_tokens adalah 4096. Untuk menaikkannya (4097–8192), hubungi manajer komersial Anda dengan menyertakan: ID akun Alibaba Cloud Anda, jenis gambar (misalnya dokumen, e-commerce, kontrak), nama model, perkiraan QPS dan volume permintaan harian, serta persentase permintaan yang melebihi 4096 token output.

API DashScope

Titik akhir

Wilayah	Titik akhir HTTP
Singapore	`POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation`
US (Virginia)	`POST https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation`
China (Beijing)	`POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation`

Konfigurasi URL dasar SDK:

Python:

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

Java (Metode 1 – konstruktor):

import com.alibaba.dashscope.protocol.Protocol;
MultiModalConversation conv = new MultiModalConversation(Protocol.HTTP.getValue(), "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1");

Java (Metode 2 – blok statis):

import com.alibaba.dashscope.utils.Constants;
Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";

Ganti domain dengan {WorkspaceId}.us-east-1.maas.aliyuncs.com untuk wilayah US (Virginia) atau {WorkspaceId}.cn-beijing.maas.aliyuncs.com untuk wilayah China (Beijing). Untuk wilayah China (Beijing), Anda tidak perlu mengatur base_url untuk panggilan SDK.

Dapatkan Kunci API dan tetapkan sebagai variabel lingkungan. Jika Anda menggunakan SDK DashScope, Anda juga harus menginstal SDK DashScope.

Tugas bawaan

API DashScope menyediakan tugas OCR bawaan melalui parameter ocr_options. Setiap tugas menggunakan prompt default yang dioptimalkan, sehingga tidak memerlukan pesan text.

Tugas	`ocr_options.task`nilai	Format output
General text recognition	`text_recognition`	Teks biasa
High-precision recognition	`advanced_recognition`	Teks biasa dengan kotak pembatas
Information extraction	`key_information_extraction`	Pasangan kunci-nilai terstruktur
Table parsing	`table_parsing`	Struktur tabel
Document parsing	`document_parsing`	Struktur dokumen
Formula recognition	`formula_recognition`	Rumus LaTeX
Multilingual recognition	`multi_lan`	Teks multibahasa

High-precision recognition

Mengembalikan teks dengan data posisi untuk setiap baris yang dikenali.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

messages = [{
            "role": "user",
            "content": [{
                "image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/ctdzex/biaozhun.jpg",
                "min_pixels": 32 * 32 * 3,
                "max_pixels": 32 * 32 * 8192,
                "enable_rotate": False}]
            }]

response = dashscope.MultiModalConversation.call(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen-vl-ocr-2025-11-20',
    messages=messages,
    ocr_options={"task": "advanced_recognition"}
)
print(response["output"]["choices"][0]["message"].content[0]["text"])

Java

// dashscope SDK version >= 2.21.8
import java.util.Arrays;
import java.util.Collections;
import java.util.Map;
import java.util.HashMap;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.aigc.multimodalconversation.OcrOptions;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;

public class Main {

    static {
        Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        Map<String, Object> map = new HashMap<>();
        map.put("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/ctdzex/biaozhun.jpg");
        map.put("max_pixels", 8388608);
        map.put("min_pixels", 3072);
        map.put("enable_rotate", false);

        OcrOptions ocrOptions = OcrOptions.builder()
                .task(OcrOptions.Task.ADVANCED_RECOGNITION)
                .build();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        map
                        )).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-ocr-2025-11-20")
                .message(userMessage)
                .ocrOptions(ocrOptions)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }

    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '
{
  "model": "qwen-vl-ocr-2025-11-20",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/ctdzex/biaozhun.jpg",
            "min_pixels": 3072,
            "max_pixels": 8388608,
            "enable_rotate": false
          }
        ]
      }
    ]
  },
  "parameters": {
    "ocr_options": {
      "task": "advanced_recognition"
    }
  }
}
'

Information extraction

Mengekstrak data kunci-nilai terstruktur dari gambar. Tentukan bidang yang akan diekstrak dalam task_config.result_schema.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

messages = [
      {
        "role":"user",
        "content":[
          {
              "image":"http://duguang-labelling.oss-cn-shanghai.aliyuncs.com/demo_ocr/receipt_zh_demo.jpg",
              "min_pixels": 3072,
              "max_pixels": 8388608,
              "enable_rotate": False
          }
        ]
      }
    ]

params = {
  "ocr_options":{
    "task": "key_information_extraction",
    "task_config": {
      "result_schema": {
          "Ride Date": "Corresponds to the ride date and time in the image, in the format YYYY-MM-DD, for example, 2025-03-05",
          "Invoice Code": "Extract the invoice code from the image, usually a combination of numbers or letters",
          "Invoice Number": "Extract the number from the invoice, usually composed of only digits."
      }
    }
  }
}

response = dashscope.MultiModalConversation.call(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen-vl-ocr-2025-11-20',
    messages=messages,
    **params)

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

Java

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

public class Main {

    static {
        Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        Map<String, Object> map = new HashMap<>();
        map.put("image", "http://duguang-labelling.oss-cn-shanghai.aliyuncs.com/demo_ocr/receipt_zh_demo.jpg");
        map.put("max_pixels", 8388608);
        map.put("min_pixels", 3072);
        map.put("enable_rotate", false);

        JsonObject resultSchema = new JsonObject();
        resultSchema.addProperty("Ride Date", "Corresponds to the ride date and time in the image, in the format YYYY-MM-DD, for example, 2025-03-05");
        resultSchema.addProperty("Invoice Code", "Extract the invoice code from the image, usually a combination of numbers or letters");
        resultSchema.addProperty("Invoice Number", "Extract the number from the invoice, usually composed of only digits.");

        OcrOptions ocrOptions = OcrOptions.builder()
                .task(OcrOptions.Task.KEY_INFORMATION_EXTRACTION)
                .taskConfig(OcrOptions.TaskConfig.builder().resultSchema(resultSchema).build())
                .build();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        map
                        )).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-ocr-2025-11-20")
                .message(userMessage)
                .ocrOptions(ocrOptions)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("ocr_result"));
    }

    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '
{
  "model": "qwen-vl-ocr-2025-11-20",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "http://duguang-labelling.oss-cn-shanghai.aliyuncs.com/demo_ocr/receipt_zh_demo.jpg",
            "min_pixels": 3072,
            "max_pixels": 8388608,
            "enable_rotate": false
          }
        ]
      }
    ]
  },
  "parameters": {
    "ocr_options": {
      "task": "key_information_extraction",
      "task_config": {
        "result_schema": {
          "Ride Date": "Corresponds to the ride date and time in the image, in the format YYYY-MM-DD, for example, 2025-03-05",
          "Invoice Code": "Extract the invoice code from the image, usually a combination of numbers or letters",
          "Invoice Number": "Extract the number from the invoice, usually composed of only digits."
        }
      }
    }
  }
}
'

Table parsing

Mengekstrak struktur tabel dari gambar.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

messages = [{
            "role": "user",
            "content": [{
                "image": "http://duguang-llm.oss-cn-hangzhou.aliyuncs.com/llm_data_keeper/data/doc_parsing/tables/photo/eng/17.jpg",
                "min_pixels": 32 * 32 * 3,
                "max_pixels": 32 * 32 * 8192,
                "enable_rotate": False}]
            }]

response = dashscope.MultiModalConversation.call(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen-vl-ocr-2025-11-20',
    messages=messages,
    ocr_options={"task": "table_parsing"}
)
print(response["output"]["choices"][0]["message"].content[0]["text"])

Java

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

public class Main {

    static {
        Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        Map<String, Object> map = new HashMap<>();
        map.put("image", "https://duguang-llm.oss-cn-hangzhou.aliyuncs.com/llm_data_keeper/data/doc_parsing/tables/photo/eng/17.jpg");
        map.put("max_pixels", 8388608);
        map.put("min_pixels", 3072);
        map.put("enable_rotate", false);

        OcrOptions ocrOptions = OcrOptions.builder()
                .task(OcrOptions.Task.TABLE_PARSING)
                .build();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        map
                        )).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-ocr-2025-11-20")
                .message(userMessage)
                .ocrOptions(ocrOptions)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }

    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '
{
  "model": "qwen-vl-ocr-2025-11-20",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "http://duguang-llm.oss-cn-hangzhou.aliyuncs.com/llm_data_keeper/data/doc_parsing/tables/photo/eng/17.jpg",
            "min_pixels": 3072,
            "max_pixels": 8388608,
            "enable_rotate": false
          }
        ]
      }
    ]
  },
  "parameters": {
    "ocr_options": {
      "task": "table_parsing"
    }
  }
}
'

Document parsing

Mengekstrak tata letak struktural dan teks dari dokumen.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

messages = [{
            "role": "user",
            "content": [{
                "image": "https://img.alicdn.com/imgextra/i1/O1CN01ukECva1cisjyK6ZDK_!!6000000003635-0-tps-1500-1734.jpg",
                "min_pixels": 32 * 32 * 3,
                "max_pixels": 32 * 32 * 8192,
                "enable_rotate": False}]
            }]

response = dashscope.MultiModalConversation.call(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen-vl-ocr-2025-11-20',
    messages=messages,
    ocr_options={"task": "document_parsing"}
)
print(response["output"]["choices"][0]["message"].content[0]["text"])

Java

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

public class Main {

    static {
        Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        Map<String, Object> map = new HashMap<>();
        map.put("image", "https://img.alicdn.com/imgextra/i1/O1CN01ukECva1cisjyK6ZDK_!!6000000003635-0-tps-1500-1734.jpg");
        map.put("max_pixels", 8388608);
        map.put("min_pixels", 3072);
        map.put("enable_rotate", false);

        OcrOptions ocrOptions = OcrOptions.builder()
                .task(OcrOptions.Task.DOCUMENT_PARSING)
                .build();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        map
                        )).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-ocr-2025-11-20")
                .message(userMessage)
                .ocrOptions(ocrOptions)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }

    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '
{
  "model": "qwen-vl-ocr-2025-11-20",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "https://img.alicdn.com/imgextra/i1/O1CN01ukECva1cisjyK6ZDK_!!6000000003635-0-tps-1500-1734.jpg",
            "min_pixels": 3072,
            "max_pixels": 8388608,
            "enable_rotate": false
          }
        ]
      }
    ]
  },
  "parameters": {
    "ocr_options": {
      "task": "document_parsing"
    }
  }
}
'

Formula recognition

Mengekstrak rumus matematika dari gambar dan mengembalikannya dalam format LaTeX.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

messages = [{
            "role": "user",
            "content": [{
                "image": "http://duguang-llm.oss-cn-hangzhou.aliyuncs.com/llm_data_keeper/data/formula_handwriting/test/inline_5_4.jpg",
                "min_pixels": 32 * 32 * 3,
                "max_pixels": 32 * 32 * 8192,
                "enable_rotate": False}]
            }]

response = dashscope.MultiModalConversation.call(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen-vl-ocr-2025-11-20',
    messages=messages,
    ocr_options={"task": "formula_recognition"}
)
print(response["output"]["choices"][0]["message"].content[0]["text"])

Java

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

public class Main {

    static {
        Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        Map<String, Object> map = new HashMap<>();
        map.put("image", "http://duguang-llm.oss-cn-hangzhou.aliyuncs.com/llm_data_keeper/data/formula_handwriting/test/inline_5_4.jpg");
        map.put("max_pixels", 8388608);
        map.put("min_pixels", 3072);
        map.put("enable_rotate", false);

        OcrOptions ocrOptions = OcrOptions.builder()
                .task(OcrOptions.Task.FORMULA_RECOGNITION)
                .build();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        map
                        )).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-ocr-2025-11-20")
                .message(userMessage)
                .ocrOptions(ocrOptions)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }

    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '
{
  "model": "qwen-vl-ocr",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "http://duguang-llm.oss-cn-hangzhou.aliyuncs.com/llm_data_keeper/data/formula_handwriting/test/inline_5_4.jpg",
            "min_pixels": 3072,
            "max_pixels": 8388608,
            "enable_rotate": false
          }
        ]
      }
    ]
  },
  "parameters": {
    "ocr_options": {
      "task": "formula_recognition"
    }
  }
}
'

General text recognition

Mengekstrak teks biasa dari gambar tanpa format struktural.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

messages = [{
            "role": "user",
            "content": [{
                "image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/ctdzex/biaozhun.jpg",
                "min_pixels": 32 * 32 * 3,
                "max_pixels": 32 * 32 * 8192,
                "enable_rotate": False}]
            }]

response = dashscope.MultiModalConversation.call(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen-vl-ocr-2025-11-20',
    messages=messages,
    ocr_options={"task": "text_recognition"}
)
print(response["output"]["choices"][0]["message"].content[0]["text"])

Java

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

public class Main {

    static {
        Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        Map<String, Object> map = new HashMap<>();
        map.put("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/ctdzex/biaozhun.jpg");
        map.put("max_pixels", 8388608);
        map.put("min_pixels", 3072);
        map.put("enable_rotate", false);

        OcrOptions ocrOptions = OcrOptions.builder()
                .task(OcrOptions.Task.TEXT_RECOGNITION)
                .build();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        map
                        )).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-ocr-2025-11-20")
                .message(userMessage)
                .ocrOptions(ocrOptions)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }

    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '
{
  "model": "qwen-vl-ocr-2025-11-20",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/ctdzex/biaozhun.jpg",
            "min_pixels": 3072,
            "max_pixels": 8388608,
            "enable_rotate": false
          }
        ]
      }
    ]
  },
  "parameters": {
    "ocr_options": {
      "task": "text_recognition"
    }
  }
}
'

Multilingual recognition

Mengenali teks dalam berbagai bahasa dari gambar.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

messages = [{
            "role": "user",
            "content": [{
                "image": "https://img.alicdn.com/imgextra/i2/O1CN01VvUMNP1yq8YvkSDFY_!!6000000006629-2-tps-6000-3000.png",
                "min_pixels": 32 * 32 * 3,
                "max_pixels": 32 * 32 * 8192,
                "enable_rotate": False}]
            }]

response = dashscope.MultiModalConversation.call(
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model='qwen-vl-ocr-2025-11-20',
    messages=messages,
    ocr_options={"task": "multi_lan"}
)
print(response["output"]["choices"][0]["message"].content[0]["text"])

Java

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

public class Main {

    static {
        Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        Map<String, Object> map = new HashMap<>();
        map.put("image", "https://img.alicdn.com/imgextra/i2/O1CN01VvUMNP1yq8YvkSDFY_!!6000000006629-2-tps-6000-3000.png");
        map.put("max_pixels", 8388608);
        map.put("min_pixels", 3072);
        map.put("enable_rotate", false);

        OcrOptions ocrOptions = OcrOptions.builder()
                .task(OcrOptions.Task.MULTI_LAN)
                .build();
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        map
                        )).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-ocr-2025-11-20")
                .message(userMessage)
                .ocrOptions(ocrOptions)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
    }

    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '
{
  "model": "qwen-vl-ocr-2025-11-20",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "https://img.alicdn.com/imgextra/i2/O1CN01VvUMNP1yq8YvkSDFY_!!6000000006629-2-tps-6000-3000.png",
            "min_pixels": 3072,
            "max_pixels": 8388608,
            "enable_rotate": false
          }
        ]
      }
    ]
  },
  "parameters": {
    "ocr_options": {
      "task": "multi_lan"
    }
  }
}
'

Streaming (DashScope)

Aktifkan keluaran streaming untuk menerima hasil secara bertahap. Metodenya berbeda-beda tergantung SDK:

SDK Python: Atur stream=True dan incremental_output=True.
SDK Java: Gunakan antarmuka streamCall.
HTTP: Atur header X-DashScope-SSE: enable.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

PROMPT_TICKET_EXTRACTION = """
Please extract the invoice number, train number, departure station, arrival station, departure date and time, seat number, seat class, ticket price, ID card number, and passenger name from the train ticket image.
You must accurately extract the key information. Do not omit or fabricate information. Replace any single character that is blurry or obscured by strong light with an English question mark (?).
Return the data in JSON format as follows: {'invoice_number': 'xxx','departure_station': 'xxx', 'arrival_station': 'xxx', 'departure_date_and_time':'xxx', 'seat_number': 'xxx','ticket_price':'xxx', 'id_card_number': 'xxx', 'passenger_name': 'xxx'},
"""

messages = [
    {
        "role": "user",
        "content": [
            {
                "image": "https://img.alicdn.com/imgextra/i2/O1CN01ktT8451iQutqReELT_!!6000000004408-0-tps-689-487.jpg",
                "min_pixels": 32 * 32 * 3,
                "max_pixels": 32 * 32 * 8192},
            {
                "type": "text",
                "text": PROMPT_TICKET_EXTRACTION
            }
        ]
    }
]

response = dashscope.MultiModalConversation.call(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen-vl-ocr-2025-11-20",
    messages=messages,
    stream=True,
    incremental_output=True,
)
full_content = ""
print("Streaming output content:")
for response in response:
    try:
        print(response["output"]["choices"][0]["message"].content[0]["text"])
        full_content += response["output"]["choices"][0]["message"].content[0]["text"]
    except:
        pass
print(f"Full content: {full_content}")

Java

import java.util.*;

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

public class Main {

    static {
        Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
    }

    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        Map<String, Object> map = new HashMap<>();
        map.put("image", "https://img.alicdn.com/imgextra/i2/O1CN01ktT8451iQutqReELT_!!6000000004408-0-tps-689-487.jpg");
        map.put("max_pixels", 8388608);
        map.put("min_pixels", 3072);
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(
                        map,
                        Collections.singletonMap("text", "Please extract the invoice number, train number, departure station, arrival station, departure date and time, seat number, seat class, ticket price, ID card number, and passenger name from the train ticket image. You must accurately extract the key information. Do not omit or fabricate information. Replace any single character that is blurry or obscured by strong light with an English question mark (?). Return the data in JSON format as follows: {\'invoice_number\': \'xxx\', \'departure_station\': \'xxx\', \'arrival_station\': \'xxx\', \'departure_date_and_time\':\'xxx\', \'seat_number\': \'xxx\',\'ticket_price\':\'xxx\', \'id_card_number\': \'xxx\', \'passenger_name\': \'xxx\'"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-vl-ocr-2025-11-20")
                .message(userMessage)
                .incrementalOutput(true)
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(item -> {
            try {
                List<Map<String, Object>> contentList = item.getOutput().getChoices().get(0).getMessage().getContent();
                if (!contentList.isEmpty()){
                    System.out.println(contentList.get(0).get("text"));
                }//
            } catch (Exception e){
                System.exit(0);
            }
        });
    }

    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

curl

curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--header 'X-DashScope-SSE: enable' \
--data '
{
    "model": "qwen-vl-ocr-2025-11-20",
    "input": {
        "messages": [
            {
              "role": "user",
              "content": [
                  {
                      "image": "https://img.alicdn.com/imgextra/i2/O1CN01ktT8451iQutqReELT_!!6000000004408-0-tps-689-487.jpg",
                      "min_pixels": 3072,
                      "max_pixels": 8388608
                  },
                  {"type": "text", "text": "Please extract the invoice number, train number, departure station, arrival station, departure date and time, seat number, seat class, ticket price, ID card number, and passenger name from the train ticket image. You must accurately extract the key information. Do not omit or fabricate information. Replace any single character that is blurry or obscured by strong light with an English question mark (?). Return the data in JSON format as follows: {\'invoice_number\': \'xxx\', \'departure_station\': \'xxx\', \'arrival_station\': \'xxx\', \'departure_date_and_time\':\'xxx\', \'seat_number\': \'xxx\',\'ticket_price\':\'xxx\', \'id_card_number\': \'xxx\', \'passenger_name\': \'xxx\'}"}
              ]
            }
        ]
    },
    "parameters": {
        "incremental_output": true
    }
}'

Parameter permintaan

Parameter	Tipe	Wajib	Deskripsi
`model`	string	Ya	Nama model. Lihat Model yang direkomendasikan untuk daftar model yang didukung.
`input.messages`	array	Ya	Array objek pesan.

Objek pesan

Setiap pesan memerlukan role (harus user) dan bidang content (string atau array). Gunakan string untuk input teks saja. Gunakan array jika input mencakup data gambar, dengan bidang-bidang berikut:

Parameter	Tipe	Wajib	Deskripsi
`image`	string	Tidak	URL, Data URL Base64, atau path lokal gambar. Lihat Mengirimkan file lokal.
`text`	string	Tidak	Prompt teks. Default: `"Please output only the text content from the image without any additional descriptions or formatting"`. Tidak diperlukan saat menggunakan tugas bawaan.
`enable_rotate`	boolean	Tidak	Atur ke `true` untuk mengoreksi gambar miring. Default: `false`.
`min_pixels`	integer	Tidak	Ambang batas piksel minimum. Lihat Kontrol resolusi gambar.
`max_pixels`	integer	Tidak	Ambang batas piksel maksimum. Lihat Kontrol resolusi gambar.

Parameter generasi

Atur parameter ini dalam objek parameters untuk panggilan HTTP.

Parameter	Tipe	Default	Deskripsi
`max_tokens`	integer	Bervariasi	Maksimum token dalam output. Lihat Batas token output. Di SDK Java, gunakan `maxTokens`.
`stream`	boolean	`false`	Aktifkan keluaran streaming. Hanya untuk SDK Python. Untuk Java, gunakan `streamCall`. Untuk HTTP, atur `X-DashScope-SSE: enable`.
`incremental_output`	boolean	`false`	Ketika `true` (direkomendasikan), setiap chunk hanya berisi konten baru. Ketika `false`, setiap chunk berisi seluruh urutan hingga saat itu. Di SDK Java, gunakan `incrementalOutput`.
`temperature`	float	`0.01`	Mengatur keragaman output. Rentang: [0, 2).
`top_p`	float	`0.001`	Ambang batas sampling nucleus. Rentang: (0, 1.0]. Atur salah satu `temperature` atau `top_p`, bukan keduanya.
`top_k`	integer	`1`	Membatasi set token kandidat selama sampling. Jika nilainya None atau lebih besar dari 100, kebijakan top_k tidak diaktifkan, dan hanya kebijakan top_p yang berlaku. Harus >= 0.
`repetition_penalty`	float	`1.0`	Hukuman untuk urutan berulang. Nilai di atas 1.0 mengurangi pengulangan.
`presence_penalty`	float	`0.0`	Mengatur pengulangan konten. Rentang: [-2.0, 2.0].
`seed`	integer	--	Menjamin hasil yang dapat direproduksi. Rentang: [0, 2^31 - 1].
`logprobs`	boolean	`false`	Atur ke `true` untuk mengembalikan probabilitas log. Model yang didukung: `qwen-vl-ocr-2025-04-13` dan seterusnya. Di SDK Java, gunakan nama yang sama. Untuk HTTP, letakkan di `parameters`.
`top_logprobs`	integer	`0`	Jumlah token paling mungkin per langkah. Rentang: [0, 5]. Hanya efektif ketika `logprobs` adalah `true`. Di SDK Java, gunakan `topLogprobs`. Untuk HTTP, letakkan di `parameters`.
`stop`	string atau array	--	Kata atau ID token penghenti. Generasi berhenti ketika string tertentu atau `token_id` muncul. Jangan mencampur string dan `token_id` dalam array yang sama.

Parameter tugas bawaan (ocr_options)

Saat menggunakan tugas bawaan, lewatkan ocr_options dalam parameters (HTTP), sebagai argumen kata kunci (SDK Python), atau melalui builder OcrOptions (SDK Java).

Parameter	Tipe	Wajib	Deskripsi
`ocr_options.task`	string	Ya	Nama tugas bawaan. Nilai valid: `text_recognition`, `key_information_extraction`, `document_parsing`, `table_parsing`, `formula_recognition`, `multi_lan`, `advanced_recognition`.
`ocr_options.task_config`	object	Tidak	Konfigurasi untuk `key_information_extraction`.
`ocr_options.task_config.result_schema`	object	Tidak	Objek JSON yang menentukan bidang yang akan diekstrak. Kunci adalah nama bidang, nilai adalah deskripsi opsional untuk meningkatkan akurasi. Mendukung hingga tiga tingkat bersarang.

result_schemacontoh:

"result_schema": {
     "invoice_number": "The unique identification number of the invoice, usually a combination of numbers and letters.",
     "issue_date": "The date the invoice was issued. Extract it in YYYY-MM-DD format, for example, 2023-10-26.",
     "seller_name": "The full company name of the seller shown on the invoice.",
     "total_amount": "The total amount on the invoice, including tax. Extract the numerical value and keep two decimal places, for example, 123.45."
}

Di SDK Java, parameter ini adalah OcrOptions. Versi minimum SDK Python DashScope adalah 1.22.2. Versi minimum SDK Java adalah 2.18.4. Untuk advanced_recognition, diperlukan SDK Java >= 2.21.8.

Tanggapan

API DashScope menggunakan format tanggapan yang identik untuk output streaming dan tidak streaming.

{
  "status_code": 200,
  "request_id": "8f8c0f6e-6805-4056-bb65-d26d66080a41",
  "code": "",
  "message": "",
  "output": {
    "text": null,
    "finish_reason": null,
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "ocr_result": {
                "kv_result": {
                  "price_excluding_tax": "230769.23",
                  "invoice_code": "142011726001",
                  "organization_code": "null",
                  "buyer_name": "Cai Yingshi",
                  "seller_name": "null"
                }
              },
              "text": "```json\n{\n    \"price_excluding_tax\": \"230769.23\",\n    \"invoice_code\": \"142011726001\",\n    \"organization_code\": \"null\",\n    \"buyer_name\": \"Cai Yingshi\",\n    \"seller_name\": \"null\"\n}\n```"
            }
          ]
        }
      }
    ],
    "audio": null
  },
  "usage": {
    "input_tokens": 926,
    "output_tokens": 72,
    "characters": 0,
    "image_tokens": 754,
    "input_tokens_details": {
      "image_tokens": 754,
      "text_tokens": 172
    },
    "output_tokens_details": {
      "text_tokens": 72
    },
    "total_tokens": 998
  }
}

Bidang	Tipe	Deskripsi
`status_code`	string	`200` menunjukkan sukses. SDK Java melemparkan pengecualian alih-alih mengembalikan bidang ini.
`request_id`	string	Identifier unik permintaan. Di SDK Java, ini adalah `requestId`.
`code`	string	Kode error. Kosong saat sukses. Hanya SDK Python yang mengembalikan bidang ini.
`output.text`	string	Selalu `null`.
`output.finish_reason`	string	`null` selama generasi, `stop` saat selesai, `length` saat dipotong.
`output.choices[].finish_reason`	string	Nilai yang sama dengan `output.finish_reason`.
`output.choices[].message.role`	string	Selalu `assistant`.
`output.choices[].message.content[].text`	string	Teks atau output terformat yang diekstrak dari model.
`output.choices[].message.content[].ocr_result`	object	Dikembalikan untuk tugas bawaan (`key_information_extraction`, `advanced_recognition`).
`output.choices[].message.content[].ocr_result.kv_result`	object	Hasil ekstraksi kunci-nilai (untuk `key_information_extraction`).
`output.choices[].message.content[].ocr_result.words_info`	array	Hasil baris teks dengan data posisi (untuk `advanced_recognition`).
`output.choices[].message.content[].ocr_result.words_info[].rotate_rect`	array	`[center_x, center_y, width, height, angle]` -- persegi panjang pembatas yang diputar.
`output.choices[].message.content[].ocr_result.words_info[].location`	array	`[x1, y1, x2, y2, x3, y3, x4, y4]` -- empat titik sudut searah jarum jam dari kiri atas.
`output.choices[].message.content[].ocr_result.words_info[].text`	string	Konten baris teks.
`output.choices[].message.logprobs`	object	Informasi probabilitas log, dikembalikan ketika `logprobs` adalah `true`.
`usage.input_tokens`	integer	Jumlah token input.
`usage.output_tokens`	integer	Jumlah token output.
`usage.characters`	integer	Tetap 0.
`usage.total_tokens`	integer	Jumlah dari `input_tokens` dan `output_tokens`.
`usage.image_tokens`	integer	Token yang sesuai dengan input gambar.
`usage.input_tokens_details.image_tokens`	integer	Token input gambar.
`usage.input_tokens_details.text_tokens`	integer	Token input teks.
`usage.output_tokens_details.text_tokens`	integer	Token output teks.

Model yang didukung

Model	Deskripsi
`qwen3.5-ocr`	Berdasarkan arsitektur Qwen3.5. Lebih cepat, lebih akurat. Peningkatan besar dalam ekstraksi informasi, penentuan posisi teks, dan dukungan percakapan multi-putaran. Panjang konteks diperpanjang hingga 128K.
`qwen-vl-ocr-latest`	Selalu mengarah ke versi terbaru.
`qwen-vl-ocr-2025-11-20`	Snapshot versi terbaru.
`qwen-vl-ocr-2025-08-28`	Versi sebelumnya.
`qwen-vl-ocr-2025-04-13`	Versi sebelumnya.
`qwen-vl-ocr-2024-10-28`	Versi sebelumnya.
`qwen-vl-ocr`	Model dasar.

Kode error

Jika pemanggilan model mengembalikan error, lihat Pesan error untuk menyelesaikan masalah.

API kompatibel OpenAI

Titik akhir

Prasyarat

Panduan cepat

Tidak streaming

Streaming

Parameter permintaan

Tanggapan

Tanggapan tidak streaming (chat.completion)

Tanggapan streaming (chat.completion.chunk)

Kontrol resolusi gambar

Batas token output

API DashScope

Titik akhir

Tugas bawaan

High-precision recognition

Information extraction

Table parsing

Document parsing

Formula recognition

General text recognition

Multilingual recognition

Streaming (DashScope)

Parameter permintaan

Tanggapan

Model yang didukung

Kode error

Tanggapan tidak streaming (`chat.completion`)

Tanggapan streaming (`chat.completion.chunk`)