The default model name for the Generate image action for the OpenAI provider is not correct.

It should be DALL-e-3 instead of GPT -4o

Steps to replicate:

1. Create a new Moodle instance.
2. Login as admin.
3. Create OpenAI provider.
4. Navigate to OpenAI provider -> Settings for Generate image action.
5. Verify the AI model.

Expected: It should be DALL-e-3

Actual: AI model is Custom with Custom model name is gpt-4o

Updated description

Normally, we have 4o and O1 for text generation. We have Dall-E-2 and Dall-E-3 for image generation.

According to: https://openai.com/index/introducing-4o-image-generation/

OpenAI decided to support image generation for 4o.

It is not available via API yet, but it will be there soon:

Developers will soon be able to generate images with GPT‑4o via the API, with access rolling out in the next few weeks.

So we need to modify our codebase to make the pre-defined models support multiple types. e.g.: Text generation, Image generation, Audio generation (in the future)

So we can easily enable them in the future