> For the complete documentation index, see [llms.txt](https://docs.powerembedded.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.powerembedded.com/administration-portal/power-pilot-gen-2/power-pilot-gen2-ai-model-creation.md).

# Power Pilot Gen2 AI Model Creation

**Power Pilot Gen2** allows you to create models using different AI providers:

* **Azure OpenAI**
* **OpenAI**
* **Gemini**
* **Claude**

<figure><img src="/files/AH9hplUxqQGYr7OpCLan" alt=""><figcaption></figcaption></figure>

Creating models follows the platform’s standard workflow, providing greater flexibility in choosing the most suitable model for each scenario.

A single AI model can be used by multiple assistants.

#### AI Model Creation

#### **Access**

To create a model, go to:

**Administration Portal > Power Pilot > AI Models > Create Model** or [click here](https://github.com/dirceuresende/docs-power-embedded-english/blob/main/administration-portal/power-pilot-ia/modelos-de-ia.md)

<figure><img src="/files/P4YOkUZ81OK9y8B7L6v8" alt=""><figcaption></figcaption></figure>

### **Model Configuration**

On the creation screen, configure the following fields:

* **Name:** internal model name (free naming)
* **Provider Model Name:** model identifier in the AI provider
* **Provider:** model source (**Azure OpenAI, OpenAI, Gemini, or Claude**)
* **API Key (BYOK):** key provided by the provider