Most LLMs output a whole bunch of tokens to help them reason through a problem, often called chain of thought, before giving the actual response. This has been shown to improve performance a lot but uses a lot of tokens
Yup, they all need to do this in case you're asking them a really hard question like: "I really need to get my car washed, the car wash place is only 50 meters away, should I drive there or walk?"
Also, if you are hundreds of thousands of miles from the center of mass of the sun, you'd feel the same force from gravity as if you were the same distance from the center of mass of a black hole (with the same mass).
Far away, the curvature of spacetime is the same, it's just that with black holes you can get waaaay closer to the center of mass whilst still being outside of it.