Use Alibaba Cloud AppFlow to create an AI assistant and a web page integration, enabling natural language interaction with the OpenClaw service and production deployment with a custom domain name.-Simple Application Server(SAS)-阿里云帮助中心

Billing

Deploying and using the OpenClaw service on a Simple Application Server instance incurs the following fees:

Simple Application Server fees: For more information, see Simple Application Server billing overview.
Model invocation fees: These fees are determined by the model provider that you choose and the pricing of the corresponding model.

Purchase an OpenClaw package

Important

If you already have a Simple Application Server instance, you can skip this step and deploy OpenClaw by resetting the system. During the reset, select the OpenClaw image from the application images. A system reset erases all data on the system disk, so be sure to back up your data first. For more information, see Reset a system. To preserve your AI assistant's memory, identity configuration, Skills, and other workspace data, see Back up and restore data for OpenClaw version upgrades.

Purchase a Simple Application Server instance with the OpenClaw application pre-installed.
On the Simple Application Server page, resource settings are pre-configured. To change them, follow these guidelines:
- Servers: The memory must be 2 GiB or higher. You can switch packages based on your needs.
- Region: The default is China (Beijing).
- Purchase Settings: The default duration is 12 months. You can change the duration based on your needs.

Configure OpenClaw

OpenClaw provides two configuration methods. Select the tab that corresponds to your image version to view the steps.

2026.5.19 and later (Recommended)

Log in to the Simple Application Server console. Click the instance ID on the server card, and then on the Server Overview page, click the Application Details tab.
In the lower-left corner of the Application Details page, click Initialize. Follow the setup wizard to complete Step 1: Model Configuration.
- Model provider: Select a provider from the drop-down list. Supported providers include Alibaba Cloud Model Studio Token Plan (Team Edition), Alibaba Cloud Model Studio AI coding plan, Alibaba Cloud Model Studio, DeepSeek, Kimi, GLM AI coding plan, and Zhipu.
- API key: Select the region that corresponds to your API key and enter the API key.
- Model: Select or manually enter a model name.
After you complete the configuration, click Configure Now.
In Step 2: Use WebUI of the setup wizard, click Allow Access in the Allow OpenClaw Port Access section to open the port. Then, click Log In to WebUI to open the OpenClaw WebUI and interact with the agent.

Important
Allowing port access exposes the service to the public internet. After initialization, you can disable public access at any time by using the Public Access toggle in the status bar at the top of the Application Details page. For more information, see How do I enable or disable public access for the OpenClaw WebUI?.
(Optional) View the token. After initialization, you can copy the full token by clicking the copy icon in the Token field in the status bar at the top of the Application Details page.

Warning
Do not share the full URL that contains the token. This link includes authentication credentials. Anyone with this link can bypass login verification and gain administrator permissions for your OpenClaw console.

Earlier than 2026.5.19

In the Simple Application Server console, click the instance ID on the server card. On the Server Overview page, click the Application Details tab.
In the OpenClaw Usage Steps section, under Allow Port Access, click Run Command to open the firewall port for the OpenClaw service.
Important
- To prevent malicious scanning and targeted attacks, OpenClaw no longer uses a fixed default port during initialization. Instead, it generates a random port. You can view the OpenClaw port number in the console.
- Allowing port access exposes the service to the public internet. You can disable public access to the WebUI with a single click. For more information, see How do I enable or disable public access for the OpenClaw WebUI?
Under Configure OpenClaw, click Run Command to configure the Alibaba Cloud Model Studio API key.
You can configure two types of Alibaba Cloud Model Studio API keys:
- AI coding plan exclusive API key (recommended): This plan provides a monthly request quota for a fixed fee. Requests that exceed the quota are blocked and do not incur additional charges.
  
  The AI coding plan currently supports models such as qwen3.5-plus, kimi-k2.5, MiniMax-M2.5, and glm-5. For a complete list of supported models, see AI coding plan overview.
- Pay-as-you-go API key.
To configure the API key, select an AI coding plan API key from the drop-down list or enter a pay-as-you-go API key. Choose a model, and then click Next.

If you manually enter an API key, ensure the selected region matches the API key's region. Otherwise, model invocation will fail.

Important
You cannot use Alibaba Cloud Model Studio Token Plans during the initial configuration. Attempting to do so will cause an error. To use a Token Plan, complete the initialization first, and then see How do I integrate Alibaba Cloud Model Studio Token Plan Team Edition with OpenClaw? for configuration instructions.
Under Access WebUI, click Run Command to get the OpenClaw WebUI URL, which you can use to interact with the agent in your browser.

You can disable public access to the WebUI with one click. For more information, see How do I enable or disable public access for the OpenClaw WebUI?.
(Optional) View the token.
Go to Application Details > Basic Configuration > View Token and click View to retrieve and save the token.

Warning
Do not share the full URL that contains the token. This link includes authentication credentials. Anyone with this link can bypass login verification and gain administrator permissions for your OpenClaw console.

Step 3: Create an AI assistant

Go to the AppFlow Workbench and click Create AI Assistant.
Select ChatFlow and enter a name for your AI assistant. In this example, the name is MoltBot.
Click Add Chat Flow and select the MoltBot (Clawdbot) basic template.
Click the ClawdBot node, keep the default configuration for the connector and action, and then click Next.
From the Select connection credential dropdown list, select Add a new credential. Configure the new credential with the token from Step 2 and save it. Select the newly created credential and click Next.
Follow the prompts on the page to enter the model name, and the public IP and port of the Simple Application Server instance. When you are finished, click Save.

Step 4: Create a web page integration

Click the Integration tab, select Web Page Integration, and then click Create Integration.
After the integration is created, click Configure in the Actions column. Customize the web page settings as needed. In the Deployment Information section, open the Deployment URL to preview the integration's appearance and test the interaction. This URL is for testing only and is valid for one month. To use it in a production environment, you must bind a custom domain name.
Open the preview link. The preview appears as follows: