VS Code

Use Alibaba Cloud Model Studio models in VS Code.

Quick Start

1. 1

   Get an API key

   Get the API key for your billing plan:

   • Token Plan Personal Edition: Create or view API Key
   • Token Plan Team Edition: Assign a seat and get the API Key
   • Pay-as-you-go: Model Studio API key
   • Coding Plan: Coding Plan API key
2. 2

   Open model management

   In VS Code, run Chat: Manage Language Models, select Add Models > Custom Endpoint, and select Chat Completions as the protocol.

3. 3

   Enter the connection details

   Follow the wizard to enter a group name, display name, and the API key for your plan. The wizard generates a secure input reference for apiKey; do not put the actual key in plaintext JSON.

4. 4

   Select a model

   Enter the connection URL and model for your billing plan:

   Token Plan

   • Base URL: https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
   • Full url: https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions
   • Models: Enter a text generation model supported by Personal Edition or Team Edition

   Pay-as-you-go

   Replace {WorkspaceId} with your actual Workspace ID.

   • Base URL: https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
   • Full url: https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/chat/completions
   • Models: for example, qwen3.8-max or qwen3.8-flash

   Coding Plan

   • Base URL: https://coding.dashscope.aliyuncs.com/v1
   • Full url: https://coding.dashscope.aliyuncs.com/v1/chat/completions
   • Models: for example, qwen3.7-plus
5. 5

   Configure model parameters

   In chatLanguageModels.json, configure the following fields:

   • vendor: customendpoint
   • apiType: chat-completions
   • models[].id: The model ID from the previous step
   • models[].name: A display name of your choice
   • models[].url: The full url from the previous step
   • models[].toolCalling, vision, maxInputTokens, maxOutputTokens: Set these according to the model's specifications

   Confirm that your plan supports the model, then check the model list. The sum of input and output tokens must not exceed the model's context length. For field descriptions, see the VS Code official documentation.

6. 6

   Verify

   Select the configured model in the Chat model picker and send "Hello". A reply confirms the connection.

FAQ