Rate Limits
Understand API usage limits and quotas.
Tier Comparison
| Tier | Requests/sec | Requests/min | Requests/hour | Chars/request |
|---|---|---|---|---|
| Free(Anonymous) | 1 | 10 | 60 | 8,000 |
| Pro€20/mo | Unlimited | Unlimited | Unlimited | Unlimited |
| Enterprise | Custom | Custom | Custom | Custom |
🚀
Pro = Truly Unlimited
With LLM.kiwi Pro, you get UNLIMITED tokens. Generous rate limits, no character limits, no surprise bills. Pay once, use all month with complete peace of mind.
Get Unlimited Access →Rate Limit Headers
Every API response includes rate limit information:
X-RateLimit-Remaining-Minute: 58
X-RateLimit-Remaining-Hour: 48
X-Response-Time: 234ms
Handling 429 Errors
When rate limited, wait and retry with exponential backoff:
import time
def call_api_with_retry(func, max_retries=3):
for i in range(max_retries):
try:
return func()
except RateLimitError:
time.sleep(2 ** i) # 1s, 2s, 4s
raise Exception("Max retries exceeded")Free vs Pro Endpoints
Free Endpoint (API Key Required):
POST /v1/free/chat/completionsPro Endpoint (API key required):
POST /v1/chat/completions