Qwen-Math model-Alibaba Cloud Model Studio(Model Studio)-阿里云帮助中心

The Qwen-Math models from Model Studio offer powerful mathematical reasoning and computational capabilities. They provide detailed, step-by-step solutions that are easy to understand and verify.

Note

We recommend using the latest general-purpose models (see Select Models) instead of the Qwen-Math models, which are based on the older Qwen2.5.
This document applies only to the China (Beijing) region, and you must use the China (Beijing) region's API key.

Models and pricing

Commercial Models

Model name	Input price	Output price	Context window	Max input	Max output	Free quota (Note)
	(per million tokens)		(tokens)
qwen-math-plus	CNY 4.00	CNY 12.00	4,096	3,072	3,072	1 million input tokens and 1 million output tokens Valid for 90 days after you activate Model Studio.
qwen-math-turbo	CNY 2.00	CNY 6.00

The free quota for each model is not shared.

For information about model rate limits, see rate limiting.

Quick start

Create an API key and export the API key as an environment variable. If you use the OpenAI SDK or DashScope SDK to make calls, install the SDK.

OpenAI compatible

Python

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"), # For security, do not hard-code your API key. Use an environment variable or a secrets management service.
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
    model="qwen-math-plus",
    messages=[{'role': 'user', 'content': 'Derive a universal solution for the quadratic equation $ Ax^2+Bx+C=0 $'}])
print(completion.choices[0].message.content)

curl

curl --location "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
    "model": "qwen-math-plus",
    "messages": [
        {
            "role": "user", 
            "content": "Derive a universal solution for the quadratic equation $ Ax^2+Bx+C=0 $"
        }
    ]
}'

DashScope

Python

from http import HTTPStatus
import dashscope


def call_with_messages():
    messages = [
        {'role': 'user', 'content': 'Derive a universal solution for the quadratic equation $ Ax^2+Bx+C=0 $'}]
    response = dashscope.Generation.call(
        model='qwen-math-plus',
        messages=messages,
        # Set result_format to 'message'.
        result_format='message',  
    )
    if response.status_code == HTTPStatus.OK:
        print(response)
    else:
        print('Request id: %s, Status code: %s, error code: %s, error message: %s' % (
            response.request_id, response.status_code,
            response.code, response.message
        ))


if __name__ == '__main__':
    call_with_messages()

Java

import java.util.Arrays;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;

public class Main {
    public static void callWithMessage()
            throws NoApiKeyException, ApiException, InputRequiredException {
        Generation gen = new Generation();
        Message userMsg = Message.builder().role(Role.USER.getValue()).content("Derive a universal solution for the quadratic equation $ Ax^2+Bx+C=0 $").build();
        GenerationParam param =GenerationParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-math-plus")
                .messages(Arrays.asList(userMsg))
                .resultFormat(GenerationParam.ResultFormat.MESSAGE)
                .build();
        GenerationResult result = gen.call(param);
        System.out.println(result);
    }


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

curl

curl --location "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
    "model": "qwen-math-plus",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": "Derive a universal solution for the quadratic equation $ Ax^2+Bx+C=0 $"
            }
        ]
    },
    "parameters": {
        "result_format": "message"
    }
}'

You can also go to the Model Studio console to try out the model.

Recommendations

Use English and LaTeX: The Qwen-Math model is designed for mathematical problems in English. Use LaTeX to represent mathematical symbols and formulas in your input.
Control content output: Partial mode provides precise control to ensure that the model's output closely follows the provided prefix. This improves the accuracy and control of the generated results.
The temperature parameter is set to 0 by default. Do not adjust this setting.
Easily extract results: The Qwen-Math model outputs the final result in a \boxed{} block by default.

Frequently asked questions

How to use the Qwen-Math model to solve math problems in images?

The Qwen-Math model does not currently support image recognition.

If an image contains a simple math problem, use the Qwen-VL or QVQ models to solve it.
If an image contains a complex math problem, first use the Qwen-VL or QVQ models to extract the text from the image. Then, use the Qwen-Math model to solve the problem.

For information about the input and output parameters of the Qwen-Math model, see the Qwen API Reference.

Where can I find detailed information about error codes?

If the model call fails and returns an error message, see Error codes for resolution.