Alibaba Cloud SDK:Build a Python development environment on Windows

1. Before you make a call, make sure that an AccessKey pair is obtained. We recommend that you use the AccessKey pair of a Resource Access Management (RAM) user. For more information, see the Create an AccessKey pair for a RAM user section of the "Create an AccessKey pair" topic.

   Important

   After you obtain the AccessKey pair of a RAM user, you must configure the AccessKey pair in environment variables. For more information, see Configure environment variables in Linux, macOS, and Windows.

2. Log on to SDK Center and select the service that you want to use. In this example, the DescribeInstanceTypeFamilies API operation of Elastic Compute Service (ECS) is called.

3. On the Parameters tab in the middle column, specify the parameters based on your business requirements. When you specify the parameters, read the information on the Document tab in the rightmost column. Make sure that you understand the usage notes of the operation and the description of each parameter. Pay attention to billing-related information. In this example, the DescribeInstanceTypeFamilies operation supports two request parameters. You must specify a value such as cn-qingdao for the RegionId parameter. The Generation parameter is optional. You can set this parameter to ecs-5, which indicates the V-series instance family. You can view the valid values of the parameters on the Document tab. Configure the parameters based on your actual business requirements.

4. On the SDK Sample Code tab in the rightmost column, select Python as the programming language and click Download Project to download the complete SDK project to your computer. Then, decompress the package.

5. Sample code:

   # -*- coding: utf-8 -*-
   import os
   import sys
   
   from typing import List
   
   from alibabacloud_ecs20140526.client import Client as Ecs20140526Client
   from alibabacloud_tea_openapi import models as open_api_models
   from alibabacloud_ecs20140526 import models as ecs_20140526_models
   from alibabacloud_tea_util import models as util_models
   from alibabacloud_tea_util.client import Client as UtilClient
   
   
   class Sample:
       def __init__(self):
           pass
   
       @staticmethod
       def create_client() -> Ecs20140526Client:
           """
           Use your AccessKey ID and AccessKey secret to initialize the client.
           @return: Client
           @throws Exception
           """
         
           config = open_api_models.Config(
           # os.environ specifies that the AccessKey ID and AccessKey secret are obtained from an environment variable.
           # Required. Make sure that the ALIBABA_CLOUD_ACCESS_KEY_ID environment variable is configured. ,
           access_key_id=os.environ['ALIBABA_CLOUD_ACCESS_KEY_ID'],
           # Required. Make sure that the ALIBABA_CLOUD_ACCESS_KEY_SECRET environment variable is configured. ,
           access_key_secret=os.environ['ALIBABA_CLOUD_ACCESS_KEY_SECRET']
           )
           config.endpoint = f'ecs.cn-qingdao.aliyuncs.com'
           return Ecs20140526Client(config)
   
       @staticmethod
       async def main_async(
               args: List[str],
       ) -> None:
           client = Sample.create_client()
           describe_instance_type_families_request = ecs_20140526_models.DescribeInstanceTypeFamiliesRequest(
               region_id='cn-qingdao',
               generation='ecs-5'
           )
           runtime = util_models.RuntimeOptions()
           try:
               # If you copy and run the sample code, write your own code to display the response of the API operation.
               await client.describe_instance_type_families_with_options_async(describe_instance_type_families_request, runtime)
           except Exception as error:
               # Handle exceptions with caution based on your actual business scenario and do not ignore exceptions in your project. The error message displayed in this example is for reference only. 
               # The error message.
               print(error.message)
               # The URL of the corresponding error diagnostics page.
               print(error.data.get("Recommend"))
               UtilClient.assert_as_string(error.message)
   
   
   def main(
           args: List[str],
   ) -> None:
       client = Sample.create_client()
       describe_instance_type_families_request = ecs_20140526_models.DescribeInstanceTypeFamiliesRequest(
           region_id='cn-qingdao',
           generation='ecs-5'
       )
       runtime = util_models.RuntimeOptions()
       try:
           # If you copy and run the sample code, write your own code to display the response of the API operation.
           response = client.describe_instance_type_families_with_options(describe_instance_type_families_request, runtime)
           print(response)
       except Exception as error:
           # Handle exceptions with caution based on your actual business scenario and do not ignore exceptions in your project. The error message displayed in this example is for reference only. 
           # The error message.
           print(error.message)
           # The URL of the corresponding error diagnostics page.
           print(error.data.get("Recommend"))
           UtilClient.assert_as_string(error.message)
   
   
   if __name__ == '__main__':
       main(sys.argv[1:])

6. Results:

7. Use Alibaba Cloud SDK for Python. For more information, see Use Alibaba Cloud SDKs for Python in an IDE.

1. Alibaba Cloud Model Studio allows you to call large language models (LLMs) by performing API operations. Alibaba Cloud Model Studio is compatible with API operations and the DashScope SDK. Before you make a call, activate Alibaba Cloud Model Studio and obtain the API key. For more information, see Manage account.

   Important

   After you obtain the API key, specify it in the environment variable. Prevent API key leaks, do not expose the API key in the code. For more information, see Set API key as environment variable.

2. Run the following command to install the SDK for Python:

   # If the execution fails, replace pip with pip3 and re-run the command.
   pip install -U openai

   If you receive the "Successfully installed ... openai-x.x.x" message, the SDK for Python is installed.

3. After you install Python and the SDK for Python, you can run the following sample code to call the Qwen API:

   import os
   from openai import OpenAI
   
   try:
       client = OpenAI(
           # os.getenv indicates that the API key is obtained from the environment variable. If you do not configure the environment variable, replace the following setting with api_key="sk-xxx:
           api_key=os.getenv("DASHSCOPE_API_KEY"),
           base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
       )
   
       completion = client.chat.completions.create(
           model="qwen-plus",
           messages=[
               {'role': 'system', 'content': 'You are a helpful assistant.'},
               {'role': 'user', 'content': 'Who are you? '}
           ]
       )
       print(completion.choices[0].message.content)
   except Exception as e:
       print(f"Error message: {e}")
       print("Reference: https://help.aliyun.com/zh/model-studio/developer-reference/error-code")

4. Output:

5. For more information about how to call the Qwen API, see OpenAI Python SDK.

This section describes how to call DeepSeek through API calls on Alibaba Cloud Model Studio. deepseek-r1 and deepseek-v3 provide 1 million free tokens. Some of the distillation models are free of charge for a limited period of time.

1. Before you make a call, activate Alibaba Cloud Model Studio and obtain the API key. For more information, see Manage account.

   Important

   After you obtain the API key, specify it in the environment variable. Prevent API key leaks, do not expose the API key in the code. For more information, see Set API key as environment variable.

2. Run the following command to install the SDK for Python:

   # If the execution fails, replace pip with pip3 and re-run the command.
   pip install -U openai

   If you receive the "Successfully installed ... openai-x.x.x" message, the SDK for Python is installed.

3. After you install Python and the SDK for Python, you can run the following sample code to call the DeepSeek:

   import os
   from openai import OpenAI
   
   client = OpenAI(
       # os.getenv indicates that the API key is obtained from the environment variable. If you do not configure the environment variable, replace the following setting with api_key="sk-xxx:
       api_key=os.getenv("DASHSCOPE_API_KEY"),
       base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
   )
   
   completion = client.chat.completions.create(
       model="deepseek-r1",  # In this example, deepseek-r1 is called. You can specify the name of the model that you want to use. 
       messages=[
           {'role': 'user', 'content': Which is larger, 9.9 or 9.11?''}
       ]
   )
   
   # Use the reasoning_content field to print the referencing process.
   print("Referencing process:")
   print(completion.choices[0].message.reasoning_content)
   
   # Use the content field to print the final answer.
   print("Final answer:")
   print(completion.choices[0].message.content)

4. Output:

5. Call the DeepSeek API. For more information, see .