AI Models
By default, the platform selects an AI model for each request based on the user's plan and what the request needs. Most apps do not need to configure models manually.
Default Selection
When an app makes an AI request without specifying a model, the platform chooses an appropriate available model. The selected model depends on the request type, required capabilities, and the user's subscription.
Higher plans can use more capable models. Guest and Free users use Lite AI, Plus users can use Standard AI, and Pro and Ultra users can use Advanced AI.
Model Tiers
Models are grouped into three tiers:
| Tier | Best for | Availability |
|---|---|---|
| Lite | Fast, lower-cost tasks such as formatting, classification, and quick summaries | Guest, Free, Plus, Pro, and Ultra |
| Standard | Balanced quality and cost for most everyday tasks | Plus, Pro, and Ultra |
| Advanced | Complex reasoning, higher-quality writing, and demanding tasks | Pro and Ultra |
Fallback Behavior
Automatic model selection includes graceful fallback. If the first model cannot handle a requested capability, such as a specific attachment type or web search, the platform can try another available model so the request still succeeds when possible.
Fallback only applies when the platform is choosing the model. If an app pins a specific model, the platform uses that model and returns an error if it cannot satisfy the request.
Model Types
The platform supports models for text, images, video, and speech. For developer-facing details, see the AI text, AI image, AI video, and AI speech references.
To customize model behavior in an app, see Model Selection.