Python 批量调用（高并发）

from openai import OpenAI
from concurrent.futures import ThreadPoolExecutor
client = OpenAI(api_key="sk-...", base_url="https://api.onefast.ai/v1")
def ask(text):
    r = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": text}],
        max_tokens=100,
    )
    return r.choices[0].message.content
with ThreadPoolExecutor(max_workers=8) as ex:
    results = list(ex.map(ask, ["你好"] * 32))

> 注意各模型的 RPM 限制；遇到 429 时指数退避重试。