diff --git a/litellm/utils.py b/litellm/utils.py
index 420f85ac7f6..b5ddce479f3 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -5639,22 +5639,23 @@ def _calculate_retry_after(
     min_timeout: int = 0,
 ) -> Union[float, int]:
     retry_after = _get_retry_after_from_exception_header(response_headers)
+    
+    # Add some jitter (default JITTER is 0.75 - so upto 0.75s)
+    jitter = JITTER * random.random()
 
     # If the API asks us to wait a certain amount of time (and it's a reasonable amount), just do what it says.
     if retry_after is not None and 0 < retry_after <= 60:
-        return retry_after
+        return retry_after + jitter
 
-    initial_retry_delay = INITIAL_RETRY_DELAY
-    max_retry_delay = MAX_RETRY_DELAY
-    nb_retries = max_retries - remaining_retries
+    # Calculate exponential backoff
+    num_retries = max_retries - remaining_retries
+    sleep_seconds = INITIAL_RETRY_DELAY * pow(2.0, num_retries)
 
-    # Apply exponential backoff, but not more than the max.
-    sleep_seconds = min(initial_retry_delay * pow(2.0, nb_retries), max_retry_delay)
-
-    # Apply some jitter, plus-or-minus half a second.
-    jitter = JITTER * random.random()
-    timeout = sleep_seconds * jitter
-    return timeout if timeout >= min_timeout else min_timeout
+    # Make sure sleep_seconds is boxed between min_timeout and MAX_RETRY_DELAY
+    sleep_seconds = max(sleep_seconds, min_timeout)
+    sleep_seconds = min(sleep_seconds, MAX_RETRY_DELAY)    
+    
+    return sleep_seconds + jitter
 
 
 # custom prompt helper function