## Documentation Index

Fetch the complete documentation index at: [/llms.txt](https://docs.cognigy.com/llms.txt)

Use this file to discover all available pages before exploring further.

As of Cognigy.AI 2026.6.0, the support for the Completions API for custom LLMs is deprecated. The full removal is planned for Cognigy.AI 2026.24.0. Switch to the `https://api.openai.com/v1/chat/completions` API instead before the removal date.

You are subject to the terms and conditions of the third-party LLM providers you are using.

To start using an OpenAI-compatible model with Cognigy.AI features, follow these steps:

1. [Add a Model](https://docs.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/openai-compatible#add-models)
2. [Apply the Model](https://docs.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/openai-compatible#apply-the-model)

##  Add Models

You can add a model using one of the following interfaces:

- [GUI](https://docs.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/openai-compatible#add-models-via-gui)
- [API](https://docs.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/openai-compatible#add-models-via-the-api)

###  Add Models via GUI

You can add a model compatible with OpenAI’s API standards to Cognigy.AI in **Build > LLM**. To add the model, you will need the following parameters:

| Parameter | Description |
| --- | --- |
| apiKey | Add an API Key from the respective provider. |
| Model | Select **Custom Model**. |
| Model Type | Select one of the following options:<br>- **Chat** — lets you use either the [Chat Completions](https://platform.openai.com/docs/api-reference/chat) or [Responses](https://platform.openai.com/docs/api-reference/responses) API for chat models.<br>- **Completion** — uses the `https://api.openai.com/v1/completions` API.<br>- **Embedding** — uses the `https://api.openai.com/v1/embeddings` API.<br>For more information, refer to the [OpenAI Text Generation Models](https://platform.openai.com/docs/guides/text-generation) documentation. |
| Model Name | Enter the name of the model supported by the respective provider. To find model names, refer to the LLM provider’s documentation. |
| Base URL | Enter the base URL of the LLM provider. For example, `https://api-inference.huggingface.co/v1/` for Hugging Face. |
| Custom Authentication Header Name | Enter the name of a custom HTTP header for authentication, such as `X-Custom-Auth`. This parameter is helpful when integrating with OpenAI-compatible models or third-party APIs that don’t accept the standard `Authorization` header. Instead of sending the API key as `Authorization: Bearer <your-api-key>`, the system will send it using your custom header name. For example, `X-Custom-Auth: <your-api-key>`. |
| API Type | Appears only when **Chat** is selected as the model type. Select one of the following API options for chat models:<br>- **Chat Completion** — uses the `https://api.openai.com/v1/chat/completions` API. This option is selected by default.<br>- **Responses** — uses the `https://api.openai.com/v1/responses` API.<br>Make sure that your LLM provider supports the selected API type. |

Apply changes. Check if the connection was set up by clicking **Test**. You can switch generative models at any time using the **Model** list without setting up a new connection. For embedding models, the selection is locked because different embedding models can generate incompatible embeddings for [Knowledge AI](https://docs.cognigy.com/ai/agents/develop/knowledge-ai/overview#embedding-model). To switch an embedding, delete the connection and create a new one.

###  Add Models via the API

You can add either a standard or custom model using the [Cognigy.AI API POST /v2.0/largelanguagemodels](https://api-trial.cognigy.ai/openapi#post-/v2.0/largelanguagemodels) request. Then, test your connection for the created model via the [Cognigy.AI API POST /v2.0/largelanguagemodels//test](https://api-trial.cognigy.ai/openapi#post-/v2.0/largelanguagemodels/-largeLanguageModelId-/test).

##  Apply the Model

To apply a model, follow these steps:

1. In the left-side menu of the Project, go to **Manage > Settings**.
2. Go to the section based on your use case for using a model:
   - **Generative AI Settings**. In the **Generative AI Settings** section, activate **Enable Generative AI Features**. This setting is toggled on by default if you have previously set up the Generative AI credentials.
   - **Knowledge AI Settings**. Use this section if you need to add a model for Knowledge AI. Select a model for the **Knowledge Search** and **Answer Extraction** features. Refer to the [list of standard models](https://docs.cognigy.com/ai/empower/llms/model-support-by-feature/) and find the models that support these features.
3. Navigate to the desired feature and select a model from the list. If there are no models available for the selected feature, the system will automatically select **None**. Save changes.

##  More Information

- [Other LLM Operations](https://docs.cognigy.com/ai/agents/develop/gen-ai-and-llms/other-operations)
- [Overview](https://docs.cognigy.com/ai/agents/develop/gen-ai-and-llms/llms)
- [All LLM Providers](https://docs.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/all-providers)
- [Model support by feature](https://docs.cognigy.com/ai/agents/develop/gen-ai-and-llms/model-support-by-feature)
- [Azure OpenAI](https://docs.cognigy.com/ai/agents/develop/gen-ai-and-llms/providers/microsoft-azure-openai)