All Products
Search

This Product

    Simple Application Server:Purchase and deploy the Hermes Agent image

    Document Center

    Simple Application Server:Purchase and deploy the Hermes Agent image

    Last Updated:Apr 16, 2026

    Hermes Agent is an open-source, self-evolving AI Agent built by Nous Research. It features a built-in learning loop: it creates skills from experience, improves itself during use, maintains persistent memory across sessions, and integrates with over 15 messaging platforms, including Telegram, Discord, Slack, WhatsApp, DingTalk, and Lark. This topic describes how to purchase a Simple Application Server with the pre-installed Hermes Agent application and complete the initial configuration.

    Important

    Hermes Agent is an open-source AI Agent. Before you use it, fully assess its security and stability and strictly comply with the license agreement to secure your system environment and data.

    Billing

    Deploying and using the Hermes Agent service on a Simple Application Server incurs the following fees:

    • Simple Application Server fees: See Simple Application Server Billing Overview.

    • Model call fees: By default, Hermes Agent calls Model Studio models. There are two main billing methods for model calls:

      • Coding Plan (Recommended): This plan features a fixed monthly fee and a monthly request quota. Calls exceeding the quota fail and are not billed, preventing unexpected costs.

        The Coding Plan currently supports models such as qwen3.5-plus, kimi-k2.5, MiniMax-M2.5, and glm-5.

      • Pay-by-token: By default, the qwen3.5-plus model is used for text and image processing.

        Important

        Enable suspend service upon resource exhaustion (Singapore only): When you enable Alibaba Cloud Model Studio (Singapore) for the first time, free quotas for various models are automatically granted. Once the free quota is exhausted, pay-by-token billing applies by default. We recommend enabling the suspend service upon resource exhaustion feature to avoid extra charges.

    Step 1: Purchase a Hermes Agent plan

    Important

    If you have already purchased a Simple Application Server, you can skip this step and deploy Hermes Agent by resetting the system (select the Hermes Agent image from the application images when you perform the reset). However, resetting the system clears all data from the system disk of your Simple Application Server. Back up your data as needed. For more information, see Reset System.

    1. Purchase a Simple Application Server with a pre-installed Hermes Agent application.

    2. The Simple Application Server page comes with preconfigured resource settings. You can change these settings as described below:

      • Servers: The memory must be 2 GiB or higher. You can switch to other plans as needed.

      • Region: The default is US (Virginia).

      • Purchase Settings: The default subscription duration is 12 months. You can change the duration as needed.

    Step 2: Configure Hermes

    1. In the Simple Application Server console, click the instance ID on the server card. On the Server Overview page, click the Application Details tab.

    2. Under Configure Hermes, click Setup to configure your Model Studio API Key.

      Configure the API Key. Select a Model Studio region, choose a Coding Plan API Key from the drop-down list or enter a pay-by-token API Key, and then click Next.

      If you enter the API Key manually, ensure the selected region matches the region of the API Key. Otherwise, model calls will fail.

    3. Under the WebUI panel, click Secure Proxy Access to get the Hermes Agent WebUI URL, which opens a web page for you to interact with Hermes Agent.

    FAQ

    Configure messaging channels

    See the Hermes Agent Messaging Channel Configuration Guide.

    Switch models

    See the Hermes Agent Model Provider Configuration Guide.

    Existing API Key not recognized

    The system automatically detects any Model Studio Coding Plan subscriptions and displays their API Keys by default. To use a pay-by-token API Key, switch to manual input.