Model Service Settings

This document was translated from Chinese by AI and has not yet been reviewed.

This page only introduces the interface functions. For configuration tutorials, please refer to the Provider Configuration tutorial in the basic tutorials.

• When using a built-in provider, you only need to fill in the corresponding secret key.

• Different providers may call the secret key by different names, such as Key, API Key, or Token, but they all refer to the same thing.

API Key

In Cherry Studio, a single provider supports multi-key round-robin usage, where keys are used in a sequential, looping manner from front to back.

• Add multiple keys separated by English commas, as shown in the example below:

sk-xxxx1,sk-xxxx2,sk-xxxx3,sk-xxxx4

You must use English commas.

API Address

When using a built-in provider, you generally do not need to fill in the API address. If you need to modify it, please strictly follow the address provided in the official documentation.

If the address provided by the provider is in the format https://xxx.xxx.com/v1/chat/completions, you only need to fill in the root address part (https://xxx.xxx.com).

Cherry Studio will automatically append the remaining path (/v1/chat/completions). Failure to fill it in correctly may result in abnormal usage.

Note: The large language model routing for most providers is unified, and generally, the following operations are not required. If the provider's API path is v2, v3/chat/completions, or another version, you can manually enter the corresponding version ending with "/" in the address bar; when the provider's request route is not the conventional /v1/chat/completions, use the complete address provided by the provider and end it with #.

That is:

• When the API address ends with /, only "chat/completions" will be appended.

• When the API address ends with #, no appending operation will be performed, and only the entered address will be used.

Adding Models

Generally, clicking the Manage button in the bottom left corner of the provider configuration page will automatically retrieve all models supported by that provider. You can then click the + sign next to a model in the retrieved list to add it to the model list.

Not all models in the pop-up list will be added when you click the management button. You need to click the + sign to the right of a model to add it to the model list on the provider configuration page before it can appear in the model selection list.

Connectivity Check

Click the check button after the API Key input box to test whether the configuration is successful.

During model checking, the last conversation model added to the model list is used by default. If the check fails, please verify if there are any incorrect or unsupported models in the model list.

After successful configuration, be sure to turn on the switch in the upper right corner, otherwise the provider will remain disabled and its corresponding models will not be found in the model list.