速率限制

X-RateLimit-Limit-Requests:    600
X-RateLimit-Remaining-Requests: 587
X-RateLimit-Limit-Tokens:      600000
X-RateLimit-Remaining-Tokens:  592104
X-RateLimit-Reset-Requests:    1745012400
X-RateLimit-Reset-Tokens:      1745012400
Retry-After:                   3

from openai import OpenAI

client = OpenAI(base_url="https://api.aisa.one/v1", api_key="sk-aisa-...")

response = client.chat.completions.with_raw_response.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Hello"}],
)
remaining = int(response.headers.get("x-ratelimit-remaining-requests", 1000))
if remaining < 50:
    # Throttle preemptively — sleep a bit before the next call
    time.sleep(1.0)
body = response.parse()