来自 AI API 的 429 Too Many Requests：用退避重试

import os
import random
import time

from openai import OpenAI, APIStatusError

client = OpenAI(
    base_url="https://api.cheaptokens.dev/v1",
    api_key=os.environ["CHEAPTOKENS_API_KEY"],
    max_retries=0,  # we retry ourselves
)

RETRYABLE = {429, 500, 502, 503, 504}


def chat_with_retry(model, messages, max_attempts=5, max_total=60.0):
    started = time.monotonic()
    for attempt in range(max_attempts):
        try:
            return client.chat.completions.create(model=model, messages=messages)
        except APIStatusError as err:
            last = attempt == max_attempts - 1
            if err.status_code not in RETRYABLE or last:
                raise
            header = err.response.headers.get("retry-after")
            if header and header.replace(".", "", 1).isdigit():
                delay = float(header) + random.uniform(0, 1)  # minimum wait + jitter
            else:
                delay = random.uniform(0, min(30.0, 2.0 ** attempt))  # full jitter
            if time.monotonic() - started + delay > max_total:
                raise
            time.sleep(delay)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.cheaptokens.dev/v1",
  apiKey: process.env.CHEAPTOKENS_API_KEY,
  maxRetries: 0, // we retry ourselves
});

const RETRYABLE = new Set([429, 500, 502, 503, 504]);
const sleep = (ms) => new Promise((r) => setTimeout(r, ms));

export async function chatWithRetry(model, messages, maxAttempts = 5, maxTotalMs = 60000) {
  const started = Date.now();
  for (let attempt = 0; attempt < maxAttempts; attempt++) {
    try {
      return await client.chat.completions.create({ model, messages });
    } catch (err) {
      const last = attempt === maxAttempts - 1;
      if (!RETRYABLE.has(err.status) || last) throw err;
      const header = Number(err.headers?.get?.("retry-after"));
      const delayMs = Number.isFinite(header) && header > 0
        ? header * 1000 + Math.random() * 1000 // minimum wait + jitter
        : Math.random() * Math.min(30000, 2 ** attempt * 1000); // full jitter
      if (Date.now() - started + delayMs > maxTotalMs) throw err;
      await sleep(delayMs);
    }
  }
}

import asyncio

limit = asyncio.Semaphore(4)  # at most 4 requests in flight


async def run(job):
    async with limit:
        return await call_model(job)  # your async call with the retry loop above