Alibaba Cloud Model Studio:Kilo CLI

Prerequisites

Before you begin:

• An Alibaba Cloud account (create one if needed; see Create an Alibaba Cloud account)

• Node.js 18.0 or later

Supported models

Kilo CLI supports the following Qwen model series through Model Studio:

For full model lists per region, see Models.

Which model to choose:

• Complex tasks (algorithm implementation, system architecture): qwen3-max-2026-01-23 or qwen3-coder-plus

• Lightweight tasks (code explanation, formatting, unit tests): qwen3-coder-next

Step 1: Activate Model Studio

1. Log in to Model Studio with your Alibaba Cloud account.

2. Read and agree to the Terms of Service. Model Studio activates automatically. If the Terms of Service do not appear, the service is already active.

If prompted for identity verification, see Verify your identity.

After activation, you receive a free quota for model inference, valid for 90 days. See Free quota for new users.

Charges apply after expiration or depletion. To prevent unexpected charges, enable the Free quota only feature.

Step 2: Install Kilo CLI

Install Kilo CLI globally:

npm install -g @kilocode/cli

Verify the installation:

kilo --version

A version number confirms successful installation.

Step 3: Get your API key

Your API key authenticates requests to Model Studio and is tied to billing. Get one from the Key Management page in your region:

• China (Beijing)

• Singapore

• US (Virginia)

Step 4: Configure the connection

Edit the Kilo CLI configuration file to connect to Model Studio.

1. Open ~/.config/kilo/config.json in a text editor:

      vim ~/.config/kilo/config.json

2. Paste the following configuration and replace <your-api-key> with your API key from Step 3. This example uses Singapore. For other regions, replace the baseURL value. To add more models, add entries to the models field (see Supported models for available models).

   Not all models are available in every region. For example, qwen3-max-2026-01-23 is unavailable in US (Virginia).

   Model Studio base URLs by region:

   Region	Base URL
   China (Beijing)	https://dashscope.aliyuncs.com/compatible-mode/v1
   Singapore	https://dashscope-intl.aliyuncs.com/compatible-mode/v1
   US (Virginia)	https://dashscope-us.aliyuncs.com/compatible-mode/v1

      {
        "$schema": "https://kilo.ai/config.json",
        "provider": {
          "bailian": {
            "npm": "@ai-sdk/anthropic",
            "name": "Alibaba Cloud Model Studio",
            "options": {
              "baseURL": "https://dashscope-intl.aliyuncs.com/apps/anthropic/v1",
              "apiKey": "<your-api-key>"
            },
            "models": {
              "qwen3-max-2026-01-23": {
                "name": "qwen3-max-2026-01-23",
                "options": {
                  "thinking": {
                    "type": "enabled",
                    "budgetTokens": 1024
                  }
                }
              },
              "qwen3-coder-plus": {
                "name": "qwen3-coder-plus"
              }
            }
          }
        }
      }

3. Save the file and restart Kilo CLI.

Step 5: Select a model and start coding

1. Run /models in Kilo CLI and search for Alibaba Cloud Model Studio.

2. Select a model, such as qwen3-max-2026-01-23 or qwen3-coder-plus.

   

3. Start a conversation by typing a prompt. Try one of these to explore your codebase:

      what does this project do?

      find and fix any bugs in the main module

   

4. As you get comfortable, try more advanced prompts:

      write unit tests for the auth module

      refactor this function to improve readability

      review the latest commit and suggest improvements

For more commands and tips, see the Kilo Code documentation.

FAQ