# Model Service Settings

This page only introduces the interface functions; for configuration tutorials, please refer to the [Provider Configuration](/docs/en-us/pre-basic/providers.md) tutorial.

{% hint style="info" %}

* When using built-in providers, you only need to fill in the corresponding secret key.
* Different providers may use different names for the secret key; secret key, Key, API Key, token, etc. all refer to the same thing.
  {% endhint %}

### API Key

In Cherry Studio, a single provider supports multi-Key polling use, and the polling method cycles through the list from front to back.

* Use an English comma to separate multiple Keys. For example:

<pre><code><strong>sk-xxxx1,sk-xxxx2,sk-xxxx3,sk-xxxx4
</strong></code></pre>

{% hint style="warning" %}
Must use **English** comma.
{% endhint %}

### 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 provider's official documentation.

> If the address given by the provider is <mark style="background-color:red;"><https://xxx.xxx.com></mark><mark style="background-color:green;">/v1/chat/completions</mark> in this format, only fill in the root address part (<mark style="background-color:red;"><https://xxx.xxx.com></mark>) is enough.
>
> Cherry Studio will automatically append the remaining path (<mark style="background-color:green;">/v1/chat/completions</mark>), and failing to fill it in as required may cause it to not work properly.

{% hint style="info" %}
Note: The large language model routes of most providers are unified, and in general the following operations are not necessary. If the provider's request route is not the usual <mark style="background-color:green;">/v1/chat/completions</mark> when, you can manually enter **the complete API address**in the API address bar, and end it with `#`.

That is:

* When the API address ends with `#` no concatenation will be performed; only the entered address will be used. <img src="/files/c548cc4b7a8b537fda1405449eb66720d7e08267" alt="" data-size="original">
  {% endhint %}

### Add Model

In general, clicking the `Manage` button at the bottom left of the provider configuration page will automatically fetch all models supported by that provider. Click the `+` button in the fetched list to add them to the model list.

{% hint style="info" %}
When you click the Manage button, not all models in the popup list will be added. You need to click the `+` on the right side of the model to add it to the model list on the provider configuration page before it can appear in the model selection list.
{% endhint %}

### Connectivity Check

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

{% hint style="info" %}
When checking models, the last chat model already added to the model list is used by default. If the check fails, please verify whether the model list contains incorrect or unsupported models.
{% endhint %}

{% hint style="danger" %}
After the configuration is successful, be sure to turn on the switch in the upper right corner; otherwise, the provider will still be in an inactive state and its corresponding model cannot be found in the model list.
{% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.cherry-ai.com/docs/en-us/pre-basic/settings/providers.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.