diff --git a/litellm/router.py b/litellm/router.py
index 6dc2a95c7da..4fadd8b6ca1 100644
--- a/litellm/router.py
+++ b/litellm/router.py
@@ -55,6 +55,7 @@ from litellm.router_utils.client_initalization_utils import (
 from litellm.router_utils.cooldown_cache import CooldownCache
 from litellm.router_utils.cooldown_callbacks import router_cooldown_handler
 from litellm.router_utils.cooldown_handlers import (
+    DEFAULT_COOLDOWN_TIME_SECONDS,
     _async_get_cooldown_deployments,
     _async_get_cooldown_deployments_with_debug_info,
     _get_cooldown_deployments,
@@ -356,7 +357,7 @@ class Router:
             self.allowed_fails = allowed_fails
         else:
             self.allowed_fails = litellm.allowed_fails
-        self.cooldown_time = cooldown_time or 60
+        self.cooldown_time = cooldown_time or DEFAULT_COOLDOWN_TIME_SECONDS
         self.cooldown_cache = CooldownCache(
             cache=self.cache, default_cooldown_time=self.cooldown_time
         )
diff --git a/litellm/router_utils/cooldown_handlers.py b/litellm/router_utils/cooldown_handlers.py
index f136707a804..d8ebaebe96f 100644
--- a/litellm/router_utils/cooldown_handlers.py
+++ b/litellm/router_utils/cooldown_handlers.py
@@ -29,7 +29,7 @@ else:
 DEFAULT_FAILURE_THRESHOLD_PERCENT = (
     0.5  # default cooldown a deployment if 50% of requests fail in a given minute
 )
-DEFAULT_COOLDOWN_TIME_SECONDS = 1
+DEFAULT_COOLDOWN_TIME_SECONDS = 5
 
 
 def _should_run_cooldown_logic(