diff --git a/litellm/litellm_core_utils/health_check_helpers.py b/litellm/litellm_core_utils/health_check_helpers.py
index 626705c7267..2ba5661db15 100644
--- a/litellm/litellm_core_utils/health_check_helpers.py
+++ b/litellm/litellm_core_utils/health_check_helpers.py
@@ -157,9 +157,7 @@ class HealthCheckHelpers:
                 **model_params,
             ),
             "completion": lambda: litellm.atext_completion(
-                **_filter_model_params(
-                    model_params=model_params, keep_max_tokens=True
-                ),
+                **_filter_model_params(model_params=model_params, keep_max_tokens=True),
                 prompt=prompt or "test",
             ),
             "embedding": lambda: litellm.aembedding(
diff --git a/litellm/litellm_core_utils/health_check_utils.py b/litellm/litellm_core_utils/health_check_utils.py
index b0e71896728..6622e901d0d 100644
--- a/litellm/litellm_core_utils/health_check_utils.py
+++ b/litellm/litellm_core_utils/health_check_utils.py
@@ -13,14 +13,10 @@ _COMPLETION_HEALTH_CHECK_STRIP_KEYS = {"messages"}
 #: ``400 Unknown parameter: 'max_tokens'``. ``atext_completion`` does accept
 #: ``max_tokens``, so the ``completion`` mode keeps it (preserves the
 #: ``BACKGROUND_HEALTH_CHECK_MAX_TOKENS`` cost cap).
-_NON_CHAT_HEALTH_CHECK_STRIP_KEYS = _COMPLETION_HEALTH_CHECK_STRIP_KEYS | {
-    "max_tokens"
-}
+_NON_CHAT_HEALTH_CHECK_STRIP_KEYS = _COMPLETION_HEALTH_CHECK_STRIP_KEYS | {"max_tokens"}
 
 
-def _filter_model_params(
-    model_params: dict, *, keep_max_tokens: bool = False
-) -> dict:
+def _filter_model_params(model_params: dict, *, keep_max_tokens: bool = False) -> dict:
     """Strip chat-only params before invoking a non-chat health check handler.
 
     ``litellm.acompletion`` is the only mode handler that consumes
diff --git a/tests/litellm/litellm_core_utils/test_health_check_utils.py b/tests/litellm/litellm_core_utils/test_health_check_utils.py
index 944f4908523..ccb4a72239a 100644
--- a/tests/litellm/litellm_core_utils/test_health_check_utils.py
+++ b/tests/litellm/litellm_core_utils/test_health_check_utils.py
@@ -43,9 +43,7 @@ def test_filter_keeps_max_tokens_for_completion_mode():
     ``litellm.atext_completion`` accepts ``max_tokens``; stripping it would
     silently remove the ``BACKGROUND_HEALTH_CHECK_MAX_TOKENS`` cost cap.
     """
-    filtered = _filter_model_params(
-        model_params=_sample_params(), keep_max_tokens=True
-    )
+    filtered = _filter_model_params(model_params=_sample_params(), keep_max_tokens=True)
 
     assert "messages" not in filtered
     assert filtered.get("max_tokens") == 5