AI Model Selection

MythTapestry offers optional AI-powered features to help you build and explore your world. No AI feature is required — you can use MythTapestry purely as a manual world-building tool. Some smart features like entity detection can run entirely locally without any external AI calls.

When you do choose to use AI features, they are powered by models available through OpenRouter, and you have full control over which model is used for each feature.

Per-feature models

Each AI feature can use a different model, letting you balance cost, speed, and quality:

Feature	What it does	Model needs
Entity extraction	Detects entity mentions in your writing	Fast text model
Relationship suggestions	Suggests new relationships based on content	Good reasoning
AI summaries	Generates summaries for content units	Good writing
Chat	Conversational Q&A about your world	Strong reasoning + large context
Query rewriting	Resolves pronouns in chat follow-ups	Fast text model
Auto-title	Generates titles for chat sessions	Fast text model

Note

Entity detection also offers a GLiNER mode that runs entirely on the server without any external AI calls. See Entity Detection for details.

Configuring models

You can set model preferences at two levels:

1. Profile level (global) — your preferred model for each feature across all worlds
2. World level — override the global preference for a specific world

Navigate to Profile > AI Preferences for global settings, or World Settings for per-world overrides.

Model selection priority

When a feature runs, the system picks a model in this order:

1. Your per-world preference (if set)
2. Your global preference (if set)
3. The feature’s configured default
4. The cheapest system-available model that supports the required capability

Tip

If you want to use a model that isn’t system-available, you can bring your own OpenRouter API key in your profile settings.

Usage quotas

Each AI feature has a usage quota that resets periodically. You can view your current usage on the Profile page.