HTTP/1.1 429 Too Many Requests
Retry-After: 1
X-Polysim-Code: RATE_LIMIT_EXCEEDED
X-Request-Id: a1b2c3d4-...
Content-Type: application/json

{"error": "Rate limit exceeded. Retry after 1s."}

import time
import requests

# Pre-throttle off the response headers — don't wait for 429.
resp = requests.get(url, headers={"X-API-Key": KEY})
remaining = int(resp.headers.get("x-ratelimit-remaining", "1"))
remaining_sec = int(resp.headers.get("x-ratelimit-remaining-per-second", "1"))
reset_at = int(resp.headers.get("x-ratelimit-reset", "0"))

# If the per-second bucket is almost drained, sleep a beat
if remaining_sec <= 1:
    time.sleep(1.0)
# If the rolling-minute bucket is almost drained, sleep until reset
elif remaining <= 5:
    sleep_for = max(0.0, reset_at - time.time())
    time.sleep(min(sleep_for, 60.0))

import time
import requests

def api_request(url, headers, json_data=None, max_retries=3):
    for attempt in range(max_retries):
        resp = requests.post(url, headers=headers, json=json_data)

        # 429 → respect Retry-After (always populated in seconds)
        if resp.status_code == 429:
            retry_after = int(resp.headers.get("Retry-After", 1))
            time.sleep(retry_after)
            continue

        if resp.status_code >= 500:
            time.sleep(2 ** attempt)  # Exponential backoff
            continue

        return resp

    raise Exception(f"Failed after {max_retries} retries")