diff --git a/tests/litellm_utils_tests/test_litellm_overhead.py b/tests/litellm_utils_tests/test_litellm_overhead.py
index 3a428e9d588..70bdcb1e95a 100644
--- a/tests/litellm_utils_tests/test_litellm_overhead.py
+++ b/tests/litellm_utils_tests/test_litellm_overhead.py
@@ -75,6 +75,7 @@ async def _vertex_ai_mocks():
         yield
 
 
+@pytest.mark.flaky(reruns=2, reruns_delay=5)
 @pytest.mark.asyncio
 @pytest.mark.parametrize(
     "model",
@@ -141,6 +142,7 @@ async def test_litellm_overhead_non_streaming(model):
     pass
 
 
+@pytest.mark.flaky(reruns=2, reruns_delay=5)
 @pytest.mark.asyncio
 @pytest.mark.parametrize(
     "model",
diff --git a/tests/local_testing/test_router.py b/tests/local_testing/test_router.py
index 6d04e6ecaa5..b01ebe7e308 100644
--- a/tests/local_testing/test_router.py
+++ b/tests/local_testing/test_router.py
@@ -1628,6 +1628,7 @@ def test_router_add_deployment():
     assert new_model_id_list[1] != new_model_id_list[0]
 
 
+@pytest.mark.flaky(reruns=2, reruns_delay=5)
 @pytest.mark.asyncio
 async def test_router_text_completion_client():
     # This tests if we re-use the Async OpenAI client