How would you design a rate limiter?

import time

class TokenBucket:
    def __init__(self, capacity, refill_rate):
        self.capacity = capacity
        self.refill_rate = refill_rate      # tokens added per second
        self.tokens = capacity
        self.last = time.monotonic()

    def allow(self, cost=1):
        now = time.monotonic()
        # refill proportional to elapsed time, capped at capacity
        self.tokens = min(self.capacity, self.tokens + (now - self.last) * self.refill_rate)
        self.last = now
        if self.tokens >= cost:
            self.tokens -= cost
            return True
        return False

# demo: capacity 5, refill 2 tokens/sec -> first 5 burst through, rest blocked
bucket = TokenBucket(capacity=5, refill_rate=2)
for i in range(8):
    print(i, "allowed" if bucket.allow() else "BLOCKED (429)")