同時リクエスト数の上限と429エラーの対処

import asyncio
import os
import random
from openai import AsyncOpenAI, RateLimitError

client = AsyncOpenAI(
    api_key=os.environ["LAOZHANG_API_KEY"],
    base_url="https://api.laozhang.ai/v1",
    max_retries=0,
)
limit = asyncio.Semaphore(10)  # 処理中のリクエスト数


async def ask(prompt, attempts=5):
    async with limit:
        for attempt in range(attempts):
            try:
                response = await client.chat.completions.create(
                    model="gpt-5.4-mini",
                    messages=[{"role": "user", "content": prompt}],
                )
                return response.choices[0].message.content
            except RateLimitError:
                if attempt == attempts - 1:
                    raise
                await asyncio.sleep(2 ** attempt + random.random())


async def main():
    prompts = [f"数字の{i}を一文で説明してください" for i in range(50)]
    results = await asyncio.gather(*(ask(p) for p in prompts))
    print(results[:3])


asyncio.run(main())