OpenAI API Error 429

HTTP 429 "Too Many Requests" means your API key sent more requests than your current rate limit allows. OpenAI enforces limits on three dimensions:

• RPM (requests per minute) — total API calls per minute
• TPM (tokens per minute) — total input + output tokens per minute
• RPD (requests per day) — daily request cap, especially on lower tiers

Check your current limits and usage at platform.openai.com/account/limits.

The OpenAI SDK handles 429 retries automatically if you set max_retries:

# Python — built-in retry
import openai
client = openai.OpenAI(max_retries=5)  # retries on 429 + 529

# Manual implementation
import time, random

def call_with_backoff(fn, max_attempts=5):
    for attempt in range(max_attempts):
        try:
            return fn()
        except openai.RateLimitError as e:
            if attempt == max_attempts - 1:
                raise
            delay = (2 ** attempt) + random.random()
            time.sleep(delay)

// TypeScript — built-in retry
import OpenAI from 'openai';
const client = new OpenAI({ maxRetries: 5 });

// Manual implementation
async function callWithBackoff(fn: () => Promise<any>, maxAttempts = 5) {
  for (let attempt = 0; attempt < maxAttempts; attempt++) {
    try {
      return await fn();
    } catch (e: any) {
      if (e?.status !== 429 || attempt === maxAttempts - 1) throw e;
      const delay = Math.pow(2, attempt) * 1000 + Math.random() * 1000;
      await new Promise(r => setTimeout(r, delay));
    }
  }
}

The Retry-After header in the 429 response tells you exactly how long to wait. The SDK reads this automatically.