What are rate limits in the OpenAI API and how do you handle them in production?

import time
import openai
from openai import OpenAI

client = OpenAI()

# 1. Exponential backoff with jitter - handle 429 errors gracefully
def call_with_retry(prompt: str, max_retries: int = 5):
    for attempt in range(max_retries):
        try:
            return client.responses.create(
                model="gpt-5.5",
                input=prompt,
            )
        except openai.RateLimitError as e:
            if attempt == max_retries - 1:
                raise
            wait = (2 ** attempt) + (0.1 * attempt)  # exponential + jitter
            print(f"Rate limited. Waiting {wait:.1f}s...")
            time.sleep(wait)

# 2. The Python SDK retries automatically by default
# Configure retry behaviour:
client = OpenAI(
    max_retries=3,       # default is 2
    timeout=60.0,        # request timeout in seconds
)

# 3. Use the Batch API for large non-time-sensitive workloads
# Batch processing: ~50% cost reduction, no rate limit impact
response = client.batches.create(
    input_file_id="file-abc123",
    endpoint="/v1/responses",
    completion_window="24h",
)