Integrating the Qwen3 model into Visual Studio Code

You can facilitate software development in Visual Studio Code with Qwen3-235B-A22B. The model can generate code, convert it to other programming languages, help you with debugging and error detection in code, analyze data, write documentation, and more.

In this tutorial, you will integrate the Qwen3-235B-A22B model into your Visual Studio Code IDE with the help of Yandex AI Studio and the Roo Code extension.

To use Qwen3-235B-A22B as your Visual Studio Code assistant, proceed as followings:

1. Set up your infrastructure.
2. Create an API key for the service account.
3. Connect to the model.
4. Test the model.

The infrastructure support fee for connecting Qwen3-235B-A22B from Visual Studio Code includes a text generation fee (see Yandex AI Studio pricing).

Set up the infrastructureSet up the infrastructure

Create a folderCreate a folder

Create a service accountCreate a service account

You will need this service account to get an API key.

Create an API key for the service accountCreate an API key for the service account

You need to create an API key for Visual Studio Code to be able to access the model.

Connect to the modelConnect to the model

1. Install the Roo Code extension in Visual Studio Code.
2. Click Roo Code in VSC left-hand panel.
3. In the window that opens, select OpenAI Compatible in the API Provider field.
4. In the Base URL field, specify https://llm.api.cloud.yandex.net/v1.
5. In the API-key field, paste the secret key value you got in the previous step.
6. In the Model field, specify gpt://<folder_ID>/qwen3-235b-a22b-fp8/latest, where <folder_ID> stands for the aistudio folder ID.
7. Click Go!.

Test the modelTest the model

As an example, let's ask Qwen to generate a script to access an AI model via the OpenAI SDK.

1. Click Roo Code in Visual Studio Code left-hand panel.

2. In the window that opens, enter your prompt in the input field below and click Send message:

   Write a script named `test.py` to make a streaming call to generate a poem about Yandex Cloud via the Python OpenAI SDK. Use model token and ID as parameters. Use `https://llm.api.cloud.yandex.net/v1` as the endpoint
   

   Result:

   import sys
   from openai import OpenAI
   
   def main():
       if len(sys.argv) != 4:
           print("Usage: python test.py <token> <model_id> <folder_id>")
           return
   
       token = sys.argv[1]
       model_id = sys.argv[2]
       folder_id = sys.argv[3]
   
       client = OpenAI(
           base_url="https://llm.api.cloud.yandex.net/v1",
           api_key=token,
           project=folder_id
       )
   
       stream = client.chat.completions.create(
           model=model_id,
           messages=[
               {"role": "user", "content": "Write a poem about Yandex Cloud"}
           ],
           stream=True
       )
   
       for chunk in stream:
           content = chunk.choices[0].delta.content
           if content:
               print(content, end="")
   
   if __name__ == "__main__":
       main()