Help Center/ MaaS/ AI Tool Access to MaaS/ Cherry Studio
Updated on 2026-11-11 GMT+08:00
View PDF
Share

Cherry Studio

With the rapid advancement of artificial intelligence, large language models (LLMs) have become a key driving force behind innovations in natural language processing applications.

To make LLMs easier for users to leverage, various model access tools and platforms have emerged. Cherry Studio is a powerful open-source multi-model desktop client that supports Windows, macOS, and Linux. It integrates multiple mainstream LLMs, including OpenAI, DeepSeek, and Gemini, and also supports running local models. It provides a wide range of features, such as conversation knowledge bases, AI image generation, translation, and seamless switching between multiple models.

This guide describes how to integrate MaaS model APIs with Cherry Studio to quickly build a personal AI assistant.

Solution Architecture

Figure 1 Solution architecture
  • The user submits a request through Cherry Studio.
  • Cherry Studio sends the request to a MaaS model.
  • The MaaS model processes the request and returns the result to Cherry Studio.
  • Cherry Studio optimizes the result and sends it to the user.

Billing

You are billed based on the number of tokens used. For details, see Inference Service Billing Items.

Constraints

This function is only available in the CN-Hong Kong region.

Prerequisites

Step 1: Downloading and Installing Cherry Studio

Download Cherry Studio from the official website or open-source address.

Step 2: Obtaining MaaS Model API for Interconnection

Obtain the model ID, API key, and API URL of the MaaS model service, which are required for connecting with Cherry Studio.

  • Obtain the Model ID and API URL
    1. Go to the MaaS Real-Time Inference page. By default, the Built-in Services page is displayed. You can also switch to the Endpoints page.
      Figure 2 Real-Time Inference page

    2. In the Operation column of the model, click API Calling and select a version. On the View API Call Description page, obtain the API URL and model ID.

  • Obtain an API Key

    If you already have an API key, you can use it. If you do not have an API key, go to the API Key Management page to create one.

Step 3: Configuring MaaS Model Information in Cherry Studio

  1. Add a MaaS provider in Cherry Studio.
    1. In the lower left corner of the Cherry Studio client, click the settings icon and click Add in Model Provider.
      Figure 3 Adding a provider
    2. Set the provider name and provider type and click OK.
      Table 1 Parameters for adding a provider

      Parameter

      Description

      Provider Name

      Enter MaaS, which can be changed as needed.

      Provider Type

      Set this parameter to OpenAI.
  2. Add the MaaS model API key and URL in Cherry Studio.
    1. In the lower left corner of the Cherry Studio client, click the settings icon.
    2. Click Huawei Cloud MaaS and configure the API key and API URL.

      Parameter

      Description

      API Key

      Enter the API key created in Step 2.

      API Host

      https://api-ap-southeast-1.modelarts-maas.com/v2

      or

      https://api-ap-southeast-1.modelarts-maas.com/openai/v1
  3. Add a model to Cherry Studio.
    1. In the Models area, click .
    2. Set the model ID, model name, and group name, and click Add Model.

      Parameter

      Description

      Model ID

      Model name obtained in Step 2.

      Model

      Custom model name

      Group Name

      Custom group name

Step 4: Using MaaS Model in Cherry Studio

  1. In the navigation pane of Cherry Studio, click and select the configured model.
    Figure 4 Selecting a model
  2. Enter message in the text box to start a conversation.

    Choose the model name in the top menu to switch models.

    Figure 5 Model Q&A example

FAQs

How long does it take for an API key to become valid after it is created in MaaS?

A MaaS API key becomes valid a few minutes after creation.