Managing Models

Models can be configured per environment. These models only work if the related API Key is also entered (and working) for the environment.

Available Language Models

Currently, the following language models can be configured:

Model	Provider	Recommended for
GPT 5.2	OpenAI	General use, complex tasks
Claude Sonnet 4.5	Anthropic	Long texts, analysis, code
Gemini 3 Pro	Google	Multimodal, fast responses

Image Models

Model	Provider	Type
GPT-Image-1	OpenAI	Image generation
DALL-E 3	OpenAI	Image generation
SDXL	Stability AI	Image generation
SD3.5	Stability AI	Image generation

AI-School aims to implement newly available models as quickly as possible within the app. We will keep administrators informed as soon as new models can be implemented.

Model Settings

Models have the following settings:

Setting	Description
Available for students	Yes/no - Determines if students can use this model
Available for Assistant API	Yes/no - Only for OpenAI language models
Available for document chat	Yes/no - Recommended: only advanced models with large context window
This is a thinking model	Yes/no - Enable to link a fast model
Fast model (alternative)	Select a faster model for default use

Models can be ordered by dragging a row in the sorting column. This order is maintained when loading models.

Thinking Model Configuration

A powerful feature is linking a thinking model to a fast model. This allows users to:

• 🚀 Use a fast model by default - Cheaper and faster for most tasks
• 🧠 Switch to the thinking model - By clicking the "think" button for complex tasks

How Does It Work?

1. Configure a thinking model: Check "This is a thinking model" on an advanced model (e.g., GPT 5.2)
2. Select a fast model: Choose a faster alternative (e.g., GPT 4.1 Mini) from the dropdown menu
3. User experience: Users see a 💡 icon in the chat to toggle between models

Benefits

Benefit	Description
Cost savings	Fast models are cheaper per token
Faster responses	Smaller models respond faster
Flexibility	Users choose when to "think deeper"
Best of both worlds	Fast for simple questions, powerful for complex tasks

Recommended Combinations

Thinking Model	Fast Model	Suitable for
GPT 5.2	GPT 4.1 Mini	General use
Claude Sonnet 4.5	Claude Haiku 3.5	Long texts, analysis
Gemini 3 Pro	Gemini 3 Flash	Multimodal tasks

Tip

The fast model doesn't need to be from the same provider. For example, you can use GPT 5.2 as thinking model with Gemini Flash as fast model.

Azure OpenAI Models

In addition to standard OpenAI models, it is also possible to use Azure OpenAI models. This is useful for schools that already have an Azure subscription or have specific compliance requirements.

Requirements

To use Azure OpenAI, you must first enter the following details in the API Keys of your environment:

Setting	Description
Azure OpenAI API Key	The API key from your Azure OpenAI resource
Azure OpenAI Instance Name	The name of your Azure OpenAI instance (e.g., my-school-openai)

Adding a Model

When creating a new model:

1. Click "New model"
2. Enter Azure in the Company field
3. An additional field appears automatically: Azure Deployment Name
4. Enter the name of your Azure deployment (e.g., gpt-4o or gpt-35-turbo)
5. The Identifier can be the same as the deployment name

Benefits of Azure OpenAI

• Data residency: Your data stays within the Azure region of your choice
• Enterprise security: Integration with Azure Active Directory and network security
• Existing billing: Use your existing Azure subscription
• Compliance: Meets various compliance standards (ISO, SOC, HIPAA)

Help with Setup

AI-School will provide assistance in setting up the models. Sometimes model identifiers need to be adjusted because a new version of the model is available. We will communicate this and set it up in your environment if desired.

Model Overview Information

Outside the admin section, there is also an overview for staff and students of all available models. You can access this by clicking Preferences and then "Information".