Maestro questions

#What is Maestro?

Maestro is the AI model at the heart of ZB Stack. It knows every AI model and every cloud. Give it a task and it finds the best way to get it done. It routes the task to the best model, puts it on the best cloud, checks the work, and tries again or goes to a stronger model when it has to. The Model Router is Maestro choosing the model. The Cloud Router is Maestro choosing the cloud.

#How is Maestro different from a router?

A router sends one request to one model. Maestro looks at the whole job: which model for each task, which cloud, whether the result passed, and what to do next when it did not. Then it learns from the answer, so the next job goes better.

#Do I need to choose the models?

No. Maestro routes every task to the right model and the right cloud, and re-routes when a result fails its check. Twelve models are in use today, from 300+ AI model endpoints across 14 leading model providers. You can choose a model yourself on any task, and Maestro uses the one you chose. See The model board.

#Does the Model Router always use a sponsored model?

It routes each task to the best model for it. A sponsored model is free, so it takes every task it does well. When another model does a task better, that one is used and the record shows the cost.

#What happens when a better model ships?

Maestro tries it on real tasks. It joins the board once it proves itself, and your AI team uses it from the next task, with nothing to change on your side.

#What does Maestro cost?

Nothing on its own. You pay what the models cost, plus 5%. That is the only fee. Work on sponsored models is free. Hosting is separate, at cost. No subscription. Every task's cost is in the record. See Pricing.

#Where does my work run?

On ZB Cloud, which runs on many clouds. Maestro chooses the one for each job. Set a place rule once, such as "stays in Bangladesh", and every job that touches that data follows it. See The Cloud Router.