Model Service Settings

This page only introduces the interface features; for configuration tutorials refer to the basic tutorial's Provider configuration tutorial.

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

• Different providers may call the secret key by different names; Secret, Key, API Key, Token, etc. all refer to the same thing.

API Key

In Cherry Studio, a single provider supports polling through multiple Keys; polling is done in list order from front to back in a loop.

• Separate multiple Keys with English commas when adding. For example:

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

You must use English commas.

API Address

When using built-in providers you generally do not need to fill in the API address; if you need to modify it, please strictly follow the address given in the official documentation.

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

Cherry Studio will automatically concatenate the remaining path (/v1/chat/completions), failure to fill it in as required may cause it not to work properly.

Note: Most providers use a unified route for large language models, so normally you do not need to perform the following operation. If the provider's request route is not the conventional /v1/chat/completions you can manually enter the full API addressin the API address field, and end it with #.

That is:

• When the API address ends with # no concatenation is performed and only the entered address is used.

Add Model

In general, click the Manage button at the bottom left of the provider configuration page to automatically fetch all models supported by that provider; from the retrieved list click the + icon to add to the model list.

When clicking the Manage button, not all models in the popup list will be added automatically; you must click the + to add them to the provider configuration's model list before they will appear in the model selection list.

Connectivity Check

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

Model checks default to using the last conversational model added to the model list; if a check fails, please verify whether there are incorrect or unsupported models in the model list.

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