OpenAI API 속도 제한 — 어떤 제한에 걸렸는지, 읽는 방법, 해결하는 재시도

HTTP/1.1 429 Too Many Requests
retry-after: 12
x-ratelimit-limit-requests: 500
x-ratelimit-remaining-requests: 0
x-ratelimit-reset-requests: 12s
x-ratelimit-limit-tokens: 200000
x-ratelimit-remaining-tokens: 143820
x-ratelimit-reset-tokens: 17s

{
  "error": {
    "message": "Rate limit reached for gpt-5.4 in organization org-... on requests per min (RPM).",
    "type": "requests",
    "code": "rate_limit_exceeded"
  }
}

import random, time
import openai

client = openai.OpenAI()

def call_with_backoff(fn, *, max_attempts=6, base=0.5, cap=30.0):
    """Retry 429s: honour Retry-After when present, jittered backoff otherwise."""
    for attempt in range(max_attempts):
        try:
            return fn()
        except openai.RateLimitError as err:
            if attempt == max_attempts - 1:
                raise
            # The server's own answer beats any formula you invent.
            retry_after = (err.response.headers or {}).get("retry-after")
            if retry_after:
                delay = float(retry_after)
            else:
                # Full jitter: sleep a random point in [0, 2^n * base], capped.
                # Without the randomness every client that failed at the same
                # instant retries at the same instant and fails again together.
                delay = random.uniform(0, min(cap, base * 2**attempt))
            time.sleep(delay)

resp = call_with_backoff(lambda: client.responses.create(
    model="gpt-5.4",
    input="Summarise this changelog in three bullets.",
))

import OpenAI from "openai";

const client = new OpenAI();
const sleep = (ms: number) => new Promise((r) => setTimeout(r, ms));

export async function callWithBackoff<T>(
  fn: () => Promise<T>,
  { maxAttempts = 6, baseMs = 500, capMs = 30_000 } = {},
): Promise<T> {
  for (let attempt = 0; ; attempt++) {
    try {
      return await fn();
    } catch (err) {
      const status = (err as { status?: number }).status;
      if (status !== 429 || attempt === maxAttempts - 1) throw err;

      const retryAfter = (err as { headers?: Headers }).headers?.get("retry-after");
      const delay = retryAfter
        ? Number(retryAfter) * 1000
        : Math.random() * Math.min(capMs, baseMs * 2 ** attempt);
      await sleep(delay);
    }
  }
}

const resp = await callWithBackoff(() =>
  client.responses.create({ model: "gpt-5.4", input: "Hello" }),
);

# Log the remaining counters on every response, not just on failures.
# By the time you see a 429 the useful signal is already an hour old.
resp = client.responses.with_raw_response.create(model="gpt-5.4", input="…")
h = resp.headers

log.info(
    "openai_quota model=%s req_left=%s tok_left=%s reset_req=%s reset_tok=%s",
    "gpt-5.4",
    h.get("x-ratelimit-remaining-requests"),
    h.get("x-ratelimit-remaining-tokens"),
    h.get("x-ratelimit-reset-requests"),
    h.get("x-ratelimit-reset-tokens"),
)

parsed = resp.parse()   # the normal response object

from openai import OpenAI

client = OpenAI(
    api_key="sk-kn-...",
    base_url="https://api.kunavo.com/v1",
)

# Same SDK, same call shape — the model string chooses the family.
client.chat.completions.create(
    model="gpt-5-6-terra",            # or claude-sonnet-5, claude-haiku-4-5, …
    messages=[{"role": "user", "content": "Hello"}],
)