Prefill Vs Decode

Which statement best explains why prefill and decode hit different bottlenecks on the same GPU?

Why does prefill's O(seq^2) attention cost saturate compute rather than bandwidth?

Spot the errors in this explanation of input vs output pricing

Why are output tokens typically 3-5× more expensive than input tokens?

For a 200-token prompt and 1000-token completion, why does decode dominate end-to-end latency?