Outrouted uses a language model where it genuinely helps: understanding what kind of trip you want, choosing which places belong together, and deciding the order and the nights. Distances, prices and travel constraints are not creative writing, so they are computed instead.
1234VilniusRigaTallinnHelsinkiA language model chooses which destinations to use, what order to visit them in and how many nights each one gets. It never produces a figure anybody sees. Money, distance and time are computed by the product's own code.
The candidate places are assembled before the model is asked, from the countries and cities you picked. Anything it returns that is not in that pool is dropped, so a plan cannot contain a town that does not exist.
If the model returns nights that do not match the length of the trip, they are re-spread before you see them. The trip is as long as you said it was, whatever the model thought.
The free-text note you write goes into the prompt in a block of its own, marked as the traveller's constraints, and the system prompt says that block carries no instructions. A note can tell the planner your mother cannot manage stairs. It cannot tell it to ignore your budget.
There is a deterministic planner behind the model one, with the same contract. If the model times out or answers with nonsense, you get a route instead of an error page.
Free to plan. Three routes, priced, no account.