> For the complete documentation index, see [llms.txt](https://docs.poweromni.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.poweromni.ai/en/administration-and-configuration/artifacts/models.md).

# Models

The **Models** menu allows you to register the AI models available in your Azure resource within Power Omni. Registering a model here makes it eligible to be used by your Agents and enables automated cost control and auditing.

<figure><img src="/files/ywhdnQhi0eOB0W6qeUoS" alt=""><figcaption></figcaption></figure>

### Overview of Registered Models

The main table displays the models that have already been configured, providing crucial financial information:

<table><thead><tr><th width="251">Field</th><th>Purpose</th></tr></thead><tbody><tr><td>Name</td><td>Identification name of the model (Ex: gpt-4o).</td></tr><tr><td>Project</td><td>The Project (Azure) to which this model is linked.</td></tr><tr><td>Input Cost (USD)</td><td>The token cost for data input (the user’s question and the provided context). This is the most common part of consumption.</td></tr><tr><td>Output Cost (USD)</td><td>The token cost for data output (the response generated by the AI).</td></tr></tbody></table>

### How to Register a New Model

To make a new AI model available for use in Power Omni, click the **Create Model** button in the upper-right corner:

<table><thead><tr><th width="188">Field</th><th>Description</th></tr></thead><tbody><tr><td>AI Models</td><td>Select from the dropdown list the AI model you want to register.</td></tr><tr><td>Name</td><td>Define a short name without spaces for the model (maximum 64 characters). This is the name that will appear in Agent selection lists.</td></tr><tr><td>Project</td><td>Link this model to one of the Projects (Azure) you have already registered. The model cost will be billed through this Azure account.</td></tr></tbody></table>

{% hint style="info" %}

### Control and Optimization

By registering models with different cost structures, you can optimize your expenses. For example, use a model with lower Input Cost for internal-use Agents with a high volume of questions.
{% endhint %}