> ## Documentation Index
> Fetch the complete documentation index at: https://docs.scitix.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Chatbox

[Chatbox](https://chatboxai.app) is a cross-platform desktop AI client for Windows, macOS, and Linux. It also provides a web version. Its built-in OpenAI provider lets you customize the API Host, so you can point Chatbox to the ScitiX Model Inference API and use ScitiX models.

Supported models include `glm-5.2` and `DeepSeek-V4-Flash`. For model pricing, see the [model catalog](https://console.scitix.ai/model-inference/models).

## Configure

The steps below use the Chatbox desktop app as an example. [Chatbox Web](https://web.chatboxai.app) uses a similar configuration flow.

1. Open **Settings** from the gear icon in the bottom-left corner, then go to **Model Provider**.

2. Select the built-in **OpenAI** provider and fill in the required fields.

   | Field    | Description                                                                                      |
   | -------- | ------------------------------------------------------------------------------------------------ |
   | API Key  | Your API Key created on the [API Keys](https://console.scitix.ai/model-inference/api_keys) page. |
   | API Host | `https://api.scitix.ai/model-api/v1`. Do not end it with `/` or `#`.                             |

3. In the model section, click **Fetch** to load the model list, then add the models you want to use, such as `glm-5.2`.

   If Chatbox cannot fetch the model list, check that the API Host and API Key are correct. You can also click **+ New** to add a model ID manually. Clicking **Reset** clears the model list.

4. Click **Check** and select a model to test the connection.

   Chatbox displays a **Model Test Results** dialog and checks capabilities such as Text, Vision, and Tool Use Request. If you see `Connection successful!`, the connection is working.

   **Model Test Results** reports Vision and Tool Use support by model. A model may pass the Text check but not support Vision. If you rely on tool/function features, choose a model with native tool calling support.

<img src="https://mintcdn.com/scitix-adfc65c2/_I6H7WpAVXPiLIwE/model-inference/media/chatbox-provider-config.png?fit=max&auto=format&n=_I6H7WpAVXPiLIwE&q=85&s=3e498e18577fc6f933f766ade786b363" alt="Chatbox — OpenAI provider pointed at ScitiX, model test passing" width="2048" height="1536" data-path="model-inference/media/chatbox-provider-config.png" />

## Verify

Start a new conversation, select a ScitiX model from the model selector at the bottom, and send a message. A normal reply confirms that the connection works. The message footer shows `OpenAI API (<model>)`.

<img src="https://mintcdn.com/scitix-adfc65c2/_I6H7WpAVXPiLIwE/model-inference/media/chatbox-chat-reply.png?fit=max&auto=format&n=_I6H7WpAVXPiLIwE&q=85&s=b0c7b0d02b13dd1a3cc5dda82f3feb65" alt="Chatbox — chatting with a ScitiX model" width="1622" height="1536" data-path="model-inference/media/chatbox-chat-reply.png" />