Alibaba Cloud Model Studio:Qwen-OCR API reference

Non-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://dashscope-us.aliyuncs.com/compatible-mode/v1
        # For China (Beijing), use https://dashscope.aliyuncs.com/compatible-mode/v1
        base_url="https://dashscope-intl.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://dashscope.aliyuncs.com/compatible-mode/v1
  baseURL: 'https://dashscope-intl.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://dashscope-intl.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

Set stream to true to receive results incrementally as the model generates them.

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://dashscope-intl.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://dashscope-intl.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://dashscope-intl.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}
}'

Non-streaming response (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
    }
  }
}

Streaming response (chat.completion.chunk)

When stream is true, the response is delivered as a series of Server-Sent Event (SSE) chunks. Each chunk follows the same structure as the non-streaming response, with these differences:

• object is always chat.completion.chunk.

• choices[].delta replaces choices[].message. The delta object has the same fields as message.

• choices[].delta.role is returned only in the first chunk.

• finish_reason is null during generation, stop on completion, or length if truncated.

• When include_usage is true, the last chunk has an empty choices array and includes the usage object.

{"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}}}

High-precision recognition

Returns text with positional data for each recognized line.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

messages = [{
            "role": "user",
            "content": [{
                "image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/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://dashscope-intl.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://dashscope-intl.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

Extracts structured key-value data from images. Specify fields to extract in task_config.result_schema.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://dashscope-intl.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://dashscope-intl.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://dashscope-intl.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

Extracts table structure from images.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://dashscope-intl.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://dashscope-intl.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://dashscope-intl.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

Extracts the structural layout and text from documents.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://dashscope-intl.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://dashscope-intl.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://dashscope-intl.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

Extracts mathematical formulas from images and returns them in LaTeX format.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://dashscope-intl.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://dashscope-intl.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://dashscope-intl.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

Extracts plain text from images without structural formatting.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

messages = [{
            "role": "user",
            "content": [{
                "image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/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://dashscope-intl.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://dashscope-intl.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

Recognizes text in multiple languages from images.

Python

import os
import dashscope

dashscope.base_http_api_url = 'https://dashscope-intl.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://dashscope-intl.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://dashscope-intl.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"
    }
  }
}
'