Open-source AI desktop client
Cherry Studio is an open-source AI desktop client. Connect it to Qwen Cloud via Token Plan (Team Edition), Coding Plan, or pay-as-you-go billing.
Go to the Cherry Studio download page, download the installation package for your operating system, and complete the installation.
Open Cherry Studio, click the settings button in the upper-right corner, and in the Model Service section click Add. Enter a provider name (for example, Token Plan (Team Edition)) and select OpenAI as the provider type.
In the Model ID field, enter the model you want to use (for example,
If you encounter errors during configuration, refer to the FAQ documentation for the corresponding billing plan:
Cause: This model only supports thinking mode, but thinking mode was not enabled when the model was called.
Solution: Enable thinking mode in the client.
Possible causes:
Install Cherry Studio
Go to the Cherry Studio download page, download the installation package for your operating system, and complete the installation.
Configure credentials
Open Cherry Studio, click the settings button in the upper-right corner, and in the Model Service section click Add. Enter a provider name (for example, Token Plan (Team Edition)) and select OpenAI as the provider type.
Token Plan (Team Edition)
| Parameter | Description |
|---|---|
| API key | Enter the Token Plan (Team Edition) dedicated API key. |
| API address | https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1 |
| Model | For available models, see Token Plan (Team Edition) supported models. |
Coding Plan
| Parameter | Description |
|---|---|
| API key | Enter the Coding Plan dedicated API key. |
| API address | https://coding-intl.dashscope.aliyuncs.com/compatible-mode/v1 |
| Model | For available models, see Coding Plan supported models. |
Pay-as-you-go
| Parameter | Description |
|---|---|
| API key | Enter your Qwen Cloud API Key. |
| API address | https://dashscope-intl.aliyuncs.com/compatible-mode/v1 |
| Model | Enter a supported model. |
Verify configuration
In the Model ID field, enter the model you want to use (for example, qwen3.7-max), and click Add. Return to the chat interface, enter any question, and confirm that the model responds normally. If it does, the configuration is complete.
FAQ
Error codes
If you encounter errors during configuration, refer to the FAQ documentation for the corresponding billing plan:
- Pay-as-you-go: Error codes and troubleshooting
- Coding Plan: Coding Plan FAQ
- Token Plan (Team Edition): Token Plan (Team Edition) FAQ
Error: The value of the enable_thinking parameter is restricted to True
Cause: This model only supports thinking mode, but thinking mode was not enabled when the model was called.
Solution: Enable thinking mode in the client.
Charges incurred despite having a free quota when using Pay-as-you-go
Possible causes:
- Incorrect API address: The free quota requires using the correct Qwen Cloud API address (
https://dashscope-intl.aliyuncs.com/compatible-mode/v1). Check that the API address in your configuration is correct. For details, see Free quota. - Per-model free quota: The free quota for each model is calculated independently and cannot be shared across models.
- Data update delay: The console updates free quota data hourly. Your free quota may already be exhausted even if the console still shows a remaining balance.