Updated on 2026-07-08 GMT+08:00

USing Started

(Optional) Modifying Security Group Rules

  • The Community Standalone Edition of this solution uses server port 3000 to access the New API service, while the CCE Container High Availability Edition uses ELB port 80 to access the New API service. It is open to all by default. Please refer to modifying the security group rules and configure the IP address whitelist.
  • This solution uses port 22 for remote login to the cloud server via SSH. If remote login is required, please refer to modifying the security group rules and configure the IP address whitelist to ensure normal access to the service.
  • After successful deployment of this solution, environment initialization is expected to take approximately 20 minutes. Deployment time may vary due to network and bandwidth factors. The service can be accessed only after deployment is completed.

New API login

  1. Log in to the development platform: Enter the access address from Quick Deployment step10 process to access the platform. For the first login, complete the system initialization by following the prompts step by step. Choose the usage mode according to your actual needs.

    Figure 1 Database check
    Figure 2 Set up administrator account
    Figure 3 Usage mode (select mode based on actual needs)
    Figure 4 Initialization completed

  2. After initialization is completed, it will automatically jump to the homepage. Click "Login" in the upper right corner, then enter the "Username" and "Password" from the previous step to log in to the New API Gateway platform.

    Figure 5 Login

    Figure 6 Enter the Username and Password

  • Users can choose the following methods for connecting to large models based on their own situation.

Integration with MaaS services

  1. Log in to the MaaS platform. This document takes deploying the DeepSeek-v3 in China-Hong Kong as an example. In the left navigation bar, select "Online Inference".

    Figure 7 MaaS platform

  2. In the preset service list, select the desired service and click "Activate Service" in the operation column on the right. When grayed out, it indicates that the service has been activated.

    Figure 8 Activate Service

  3. After successful activation, select the desired service in the service list, click "Usage Instructions", and choose "Standard Interface" as the interface type in the pop-up window to obtain the API address and model name.

    Figure 9 Usage Instructions

  4. When invoking model services deployed on MaaS, you need to fill in the API Key for interface authentication. In the left navigation bar, click "API Key Management" (you can create up to 30 keys. Each key is only displayed once upon creation, so please ensure it is properly saved. If a key is lost, it cannot be retrieved, and you will need to create a new API Key to obtain a new access key).

    Figure 10 API Key Management

  5. On the "API Key Management" page, click "Create API Key" in the upper-right corner, fill in the label (custom label for the API Key; labels must be unique and cannot be duplicated. Only uppercase and lowercase English letters, numbers, underscores, and hyphens are supported, with a length range of 1–100 characters) and description (custom description for the API Key), then click "OK." The label and description information cannot be modified after creation.

    Figure 11 Create API Key

  6. Integrate with the New API Gateway. Open the New API Gateway platform, click "Channel Management" followed by "Add Channel" in sequence, fill in the information in the pop-up window as shown in the figure below, and then click "Submit" when done.

    When adding a channel, if the type selected is OpenAI, choose the "OpenAI" interface corresponding to Figure 9 Usage Instructions to obtain the API address and model name.

    Figure 12 Add Huawei Cloud MaaS.

Basic Usage of New API

Taking token and channel addition as an example, please refer to the official guide for more detailed instructions.

  1. Configure the token as shown in the figure below.

    Figure 13 Add token

  2. Configure the channel as shown in the figure below.

    Figure 14 Add channel
    Figure 15 Test channel