Connect Alibaba Cloud Qwen to OpenClaw in 2 Minutes

Setting up a new AI provider often feels like a chore when you just want to get to the coding part. Dealing with different billing plans and region-specific endpoints can slow you down.

If you are looking to use Qwen or other models through Alibaba Cloud’s Model Studio, this guide helps you get running quickly. The Model Studio provider gives you access to Alibaba’s own Qwen series and several third-party models. You can choose between two billing plans: Standard (pay-as-you-go) and Coding Plan (subscription).

Quick start

Standard (pay-as-you-go)

# China endpoint
openclaw onboard --auth-choice modelstudio-standard-api-key-cn

# Global/Intl endpoint
openclaw onboard --auth-choice modelstudio-standard-api-key

Coding Plan (subscription)

# China endpoint
openclaw onboard --auth-choice modelstudio-api-key-cn

# Global/Intl endpoint
openclaw onboard --auth-choice modelstudio-api-key

After onboarding, set a default model:

{
  agents: {
    defaults: {
      model: { primary: "modelstudio/qwen3.5-plus" },
    },
  },
}

Plan types and endpoints

The provider automatically selects the right endpoint based on your auth choice. If you have a specific requirement, you can override this with a custom baseUrl in your configuration.

Plan	Region	Auth choice	Endpoint
Standard (pay-as-you-go)	China	modelstudio-standard-api-key-cn	dashscope.aliyuncs.com/compatible-mode/v1
Standard (pay-as-you-go)	Global	modelstudio-standard-api-key	dashscope-intl.aliyuncs.com/compatible-mode/v1
Coding Plan (subscription)	China	modelstudio-api-key-cn	coding.dashscope.aliyuncs.com/v1
Coding Plan (subscription)	Global	modelstudio-api-key	coding-intl.dashscope.aliyuncs.com/v1

Get your API key

You can find your keys in the console. Make sure you are looking at the correct region:

• China: bailian.console.aliyun.com
• Global/Intl: modelstudio.console.alibabacloud.com

Available models

There are several models available depending on your needs. Some options like qwen3.5-plus and kimi-k2.5 support image input. Context windows for these models range from 200K to 1M tokens.

• qwen3.5-plus (default) — Qwen 3.5 Plus
• qwen3-coder-plus, qwen3-coder-next — Qwen coding models
• GLM-5 — GLM models via Alibaba
• Kimi K2.5 — Moonshot AI via Alibaba
• MiniMax-M2.7 — MiniMax via Alibaba

Environment note

If you run the Gateway as a daemon using launchd or systemd, you must ensure that the MODELSTUDIO_API_KEY is available to that specific process. You can handle this by placing the key in ~/.openclaw/.env or by using env.shellEnv.

Need help with your configuration? Try the AI Setup Assistant.

下一步

• Provider Configuration
• Model Selection Guide