# Create a Deka LLM This section explains how to create a Deka LLM for the SME project type in the **Service Portal AI**. On the **Service Portal AI** page, open the **LLM** menu from the left navigation panel. The LLM page displays the list of available Large Language Models. If no LLM has been created, an empty state message appears. Click **Create LLM** to start creating a new Deka LLM.

On the **LLM** page, select **+ Create LLM** to begin the LLM creation process.

The **Team Name** field is used to specify the name of the team that will use the LLM model. Enter the team name in the provided field.

The **Select Models** section is used to select one or more models for the LLM. This section displays a list of available models, and more than one model can be selected. To help narrow down the list of models, the following options are available: * **Search Models**\ Filters the model list based on the entered keyword. * **Filter by type**\ Filters the model list based on the selected model type. * **Quick Presets**\ Filters the model list based on predefined categories.

The available model types include:

Column	Description
Chat	Functions to display models designed for interactive conversations.
Code	Functions to display models optimized for programming. This type of model is used for code generation, debugging, code explanation, or assisting developer tasks.
Vision	Functions to display models capable of processing figures/images.
Embedding	Functions to display models that generate vector representations of text. These are used for semantic search, recommendations, clustering, or integration with vector databases.

After the model list is filtered, models can be selected directly from the displayed list. Selected models are marked accordingly.

The **Tokens (M)** field is used to enter the number of tokens allocated for the selected model. This field appears after a model is selected. The entered token value is used to calculate the estimated cost, which is displayed in the **Cost Estimation** section.

The **Billing Type** field is used to select the billing method for the LLM. Two billing types are available. The displayed fields depend on the selected billing type.

Column	Description
Pay Per Use (PPU)	Uses a pay-per-use billing method. Selecting this option displays the Amount of Topup field.
Trial	Uses a trial billing method. Selecting this option displays the Voucher Code field.

The **Purpose of Use** field is used to specify the intended use of the LLM. This field provides a list of predefined purpose categories that can be selected. The available options are grouped by category.

Once all required fields have been completed, select **Submit** to proceed with the LLM creation process. Select **Cancel** to cancel the LLM creation process.

If the LLM is successfully created, a notification appears with the message **“LLM has been successfully created”**. The page is then automatically redirected to the **LLM details** page.

For more information about Deka LLM, click [this link](https://docs.cloudeka.ai/deka-llm/introduction). --- # 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.cloudeka.ai/starter-guide/create-a-deka-llm.md?ask= ``` 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.