It seems to just be a wrapper over or-tools and other solvers from their landing page, with the difference being it run on their servers versus your hardware. Their website does not mention what hardware is allocated per model (which determine speed of solving) nor any limit on model size.
Our version of a Solver as a Service deals with cases of up to 390'000 shifts in a single dataset for shift scheduling and 30'000 visits for vehicle routing problems.
Some our customers want to go even higher, and we're working on that.