Overview
Every AI feature in Creator works with a specific model, and Creator picks it for you: there is nothing to choose when you generate a brick, translate a lesson or create an image.
Who decides that model:
- The platform authorises, for each feature, which models may be used and which one is used by default.
- Your organization picks, from that list, the one it prefers for each feature.
- Creator applies that choice on every operation. If your organization hasn't chosen anything, the platform default is used.
In personal scope there is no choice: the platform default is always used.
Where it is chosen
The choice is no longer made in Creator: it is made once in your account and applies to every application.
- Open Organization > AI Models in your account
- You'll see each application's AI features, the models the platform authorises for each of them and which one is in use
- Pick the model for the features you want to change
- Changes take effect immediately for all organization members
Any member can look at that screen; changing the choice is up to the owner and the administrators.
Creator's AI features
| Feature | What it does |
|---|---|
| Content generation | Bricks, minigames and question import |
| Text processing | Evaluations, text transformations and short tasks |
| Code generation | Interactive HTML embeds from a prompt |
| Image generation | Images from a description |
| Course writing | The prose of the course generator; being a long job, the model is fixed when it starts and doesn't change midway |
| Content translation | Translating lessons and content into other languages |
| Voice-over | Turning text into audio |
| Transcription | Turning audio into text |
Available models
Depending on the feature, models come from several providers:
- OpenAI — GPT models, images and transcription
- Anthropic — Claude models
- Google — Gemini models
- ElevenLabs — voices for voice-over
- Freepik — images
Which models each feature accepts is decided by the platform, and the current list is always visible on the AI Models screen. When a model is retired, the features that had it selected fall back to their feature's default model.
Different models have different credit costs. More capable models typically cost more credits per operation. See Plans, credits and billing for current pricing.
Considerations
- Speed vs quality — Smaller models are faster but may produce lower quality output
- Cost — Larger models consume more credits per operation
- Capability — Some tasks, such as generating complete courses, benefit from more capable models
- Consistency — Changing model changes the tone and format of the output: keeping the same one gives more uniform content