> ## 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.

# LangBot

> Learn how to add an OpenAI model provider in LangBot, set a custom request URL, and connect multi-platform messaging bots to ScitiX models.

[LangBot](https://github.com/langbot-app/LangBot) is an open-source multi-platform messaging bot platform that supports QQ, WeCom, Feishu, DingTalk, Discord, Slack, and more. Its **OpenAI** model provider supports a custom request URL, so you can connect LangBot to ScitiX Model Inference.

This guide uses `glm-5.2` as an example. For the full model list and pricing, see [Models](https://console.scitix.ai/model-inference/models).

## Configure

Create an API Key on the [API Keys](https://console.scitix.ai/model-inference/api_keys) page. Open the LangBot admin panel, go to **Settings > Models**, choose **Add Provider**, and fill in:

| Field         | Value                                                                                           |
| ------------- | ----------------------------------------------------------------------------------------------- |
| Provider Name | A custom name, such as `scitix`                                                                 |
| Provider Type | **OpenAI**                                                                                      |
| Request URL   | `https://api.scitix.ai/model-api/v1`                                                            |
| API Key       | Your API Key created on the [API Keys](https://console.scitix.ai/model-inference/api_keys) page |

<img src="https://mintcdn.com/scitix-adfc65c2/pbKnxHSYUfSFiSQg/model-inference/media/langbot-add-provider.png?fit=max&auto=format&n=pbKnxHSYUfSFiSQg&q=85&s=0d1873788a878c8635a2d326cca6980d" alt="LangBot OpenAI provider with Request URL pointed to ScitiX" style={{ width: "60%", height: "auto" }} width="1664" height="1482" data-path="model-inference/media/langbot-add-provider.png" />

After saving the provider, choose **Add Model** under that provider and enter the model name `glm-5.2`. Enable capabilities such as **Function Call** if your scenario requires them.

## Verify

When you add a model, LangBot sends a connectivity test to the ScitiX endpoint. A green check mark, such as `3.1s`, means the connection is successful.

<img src="https://mintcdn.com/scitix-adfc65c2/pbKnxHSYUfSFiSQg/model-inference/media/langbot-add-model.png?fit=max&auto=format&n=pbKnxHSYUfSFiSQg&q=85&s=92a2ab841c38b0ea0480b7de5047359d" alt="LangBot adds glm-5.2 and passes the connectivity test" style={{ width: "50%", height: "auto" }} width="752" height="826" data-path="model-inference/media/langbot-add-model.png" />

Then set this model as the conversation model in **Pipelines**, bind a messaging platform under **Bots**, and start using it.

## FAQ

* **Provider Type**:
  Select **OpenAI**. Its Request URL is configurable, so no dedicated ScitiX preset is required.
* **Tool or agent capabilities**:
  Choose a model that supports tool calling and enable **Function Call** when needed. `glm-5.2` supports tool calling.
* **Personal WeChat or personal QQ adapters**:
  Third-party protocol adapters may carry compliance and account-ban risks. For production use, prefer official channels such as Feishu, DingTalk, WeCom, public accounts, QQ official bots, Discord, or Slack.