Cost & Rate Limit Management — per-tenant ledger

from dataclasses import dataclass

PRICING_PER_1M = {
    "gpt-5.4": {"prompt": 2.50, "completion": 15.00},
    "gpt-4.1": {"prompt": 2.00, "completion": 8.00},
    "gpt-4o-mini": {"prompt": 0.15, "completion": 0.60},
}

@dataclass
class CostTracker:
    total_cost_usd: float = 0.0
    total_prompt_tokens: int = 0
    total_completion_tokens: int = 0
    request_count: int = 0

    def record(self, model: str, usage: dict) -> float:
        p = usage.get("prompt_tokens", 0)
        c = usage.get("completion_tokens", 0)
        pricing = PRICING_PER_1M.get(model, {"prompt": 0, "completion": 0})
        cost = p * pricing["prompt"] / 1_000_000 + c * pricing["completion"] / 1_000_000
        self.total_cost_usd += cost
        self.request_count += 1
        return cost

import asyncio, random

async def retry_with_backoff(func, max_retries=6, initial_delay=1.0):
    delay = initial_delay
    for attempt in range(max_retries + 1):
        try:
            return await func()
        except httpx.HTTPStatusError as e:
            if e.response.status_code not in (429, 500, 502, 503, 504):
                raise
            if attempt == max_retries: raise
            # Honor Retry-After header
            retry_after = e.response.headers.get("Retry-After")
            sleep_time = float(retry_after) if retry_after else delay * (0.5 + random.random())
            await asyncio.sleep(min(sleep_time, 60.0))
            delay = min(delay * 2, 60.0)