Why nobody will give you a price on the phone
Because "a two-minute video" describes the runtime and nothing else. Two minutes of one person talking in one room and two minutes covering a product launch across three cities are separated by an order of magnitude, and the runtime is identical.
What a serious production company does instead is ask what the video has to accomplish, then scope backward from that. The number comes out of the scope. If the number comes first, the scope will get cut to fit it, and you will find out which parts got cut in the edit.