# Create a Templated Model

Now that you have a handful of validation examples and a template, it's time to create a [templated model](/key-concepts/models.md#templated-models) for evaluation.

{% hint style="info" %}
Make sure you have set up your OpenAI integration (or another [Model Provider](/key-concepts/model-providers.md)).
{% endhint %}

Navigate to the models tab and press +. In the dropdown that appears, choose "Apple a template."

<figure><img src="/files/Cgm5fOYdZYL1rOW0DmXY" alt=""><figcaption></figcaption></figure>

In the dialog that appears, the template you created should be selected automatically.

For the platform, choose OpenAI (or the [model provider](/key-concepts/model-providers.md) of your choice).

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

You can choose any model. We'll go with GPT-4 Omni.

Leave the default name and press "Add to project."

<figure><img src="/files/symKbGSLQM8ZGHjpCGCf" alt=""><figcaption></figcaption></figure>

Immediately, Entry Point will start [evaluating](/key-concepts/evaluation.md) your model against your validation examples.

Open the new templated model from its name in the table.

<figure><img src="/files/i2kfGMtnPhTkOjBcGL1k" alt=""><figcaption></figcaption></figure>

At the bottom of this detail view, you will see the Evaluation section.&#x20;

<figure><img src="/files/jo5rkYLqa4H7EmI15eMc" alt=""><figcaption></figcaption></figure>

After a moment, you should see the results appear.

In the next part, we will review the results and see how our model performed.


---

# 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.entrypointai.com/guides/evaluate-a-prompt/create-a-templated-model.md?ask=<question>
```

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.