Models & Cost
Configuration
Last updated: October 23, 2026
All settings are optional. The defaults are sensible.
Generation
- Max output tokens (default 16000): upper bound on the layout JSON the model may return. Larger pages need more.
- Temperature (default 0.3): lower values give steadier, more valid JSON.
- Request timeout (default 150 seconds): how long to wait for the model before failing.
- Debug (default off): include the raw model output in the response for troubleshooting.
- Prompt size: Full or Smart. See Daily Limits and Prompt Size.
- Offer real site links: turn the feature off for the whole site.
Business profile
Name, what you offer, who it is for, where, and proof points. See Real Links, Business Profile and Industry Packs.
Daily limits
Daily limit per user and Daily limit for the whole site. 0 means no limit.