Rate Limits

Real200 implements rate limiting on API requests to ensure service stability and fairness.

Rate Limit Metrics

Metric	Description
RPM (Requests Per Minute)	Maximum requests per minute
TPM (Tokens Per Minute)	Maximum tokens per minute

Default Limits

User Type	RPM	TPM
Free Users	60	50,000
Paid Users	600	500,000
Enterprise	Contact for custom	Contact for custom

:::tip Increase Limits

To increase rate limit thresholds, contact support or submit a request in the console.

:::

Rate Limit Response

When limits are exceeded, the API returns 429 Too Many Requests:

{
  "error": {
    "message": "Request rate limit exceeded (RPM: 60). Please retry later.",
    "type": "rate_limit_exceeded",
    "code": "rate_limit_exceeded"
  }
}

Retry Strategy

Recommended Exponential Backoff strategy:

import time
import random

def call_with_retry(func, max_retries=3):
    for attempt in range(max_retries):
        try:
            return func()
        except RateLimitError:
            if attempt == max_retries - 1:
                raise
            wait = (2 ** attempt) + random.uniform(0, 1)
            time.sleep(wait)