Rate Limits

Rate limits protect the API and ensure fair usage across all users.

Handling Rate Limits

When you exceed the rate limit, the API returns a 429 status code with a rate_limit_error:

{
    "error": {
        "code": 429,
        "message": "Rate limit exceeded",
        "type": "rate_limit_error",
        "fallback_suggestion": "retry after 60 seconds"
    }
}

Implement exponential backoff when you receive a 429 response:

import time
import requests

def make_request_with_retry(url, headers, payload, max_retries=3):
    for attempt in range(max_retries):
        response = requests.post(url, headers=headers, json=payload)

        if response.status_code == 429:
            wait_time = 2 ** attempt * 30  # 30s, 60s, 120s
            print(f"Rate limited. Retrying in {wait_time}s...")
            time.sleep(wait_time)
            continue

        return response

    raise Exception("Max retries exceeded")

Best Practices

  • Implement exponential backoff for 429 responses
  • Use callback_url (webhooks) instead of frequent polling to reduce request volume
  • Space out generation requests rather than sending bursts
  • Monitor your credit usage via the EvoLink dashboard

Need Higher Limits?

Contact our sales team for custom rate limits and dedicated infrastructure.

Get Early Access