diff --git a/litellm/proxy/spend_tracking/spend_tracking_utils.py b/litellm/proxy/spend_tracking/spend_tracking_utils.py
index 6a0736ea9dc..3fd20bb7e81 100644
--- a/litellm/proxy/spend_tracking/spend_tracking_utils.py
+++ b/litellm/proxy/spend_tracking/spend_tracking_utils.py
@@ -1182,10 +1182,6 @@ def _sanitize_error_information_for_spend_logs(
       ``'input'`` / ``'messages'`` / ``'prompt'`` values *and* Pydantic v2
       ``input_value=...`` assignments inside both ``error_message`` and
       ``traceback`` so prompts cannot leak through either field.
-    - An unknown-model rejection (``ProxyModelNotFoundError``) persists its
-      ``spend_log_error_message``, which names the route and the rejection
-      without the raw client ``model`` string, matching the ``unknown-model``
-      placeholder in the row's ``model`` column.
 
     Scoped to the spend-log path — OTEL/Datadog/etc. callbacks still receive
     the untruncated error per ``LITELLM_TRUNCATION_DB_SAFEGUARD_NOTE``.
diff --git a/tests/test_litellm/proxy/spend_tracking/test_spend_tracking_utils.py b/tests/test_litellm/proxy/spend_tracking/test_spend_tracking_utils.py
index 056bbc87cd3..e9bbaf0c96e 100644
--- a/tests/test_litellm/proxy/spend_tracking/test_spend_tracking_utils.py
+++ b/tests/test_litellm/proxy/spend_tracking/test_spend_tracking_utils.py
@@ -2771,7 +2771,9 @@ def test_sanitize_error_information_persists_no_raw_model_for_an_unknown_model_r
 ):
     error_information: Final = StandardLoggingPayloadSetup.get_error_information(original_exception=original_exception)
 
-    sanitized: Final = _sanitize_error_information_for_spend_logs(error_information, original_exception=original_exception)
+    sanitized: Final = _sanitize_error_information_for_spend_logs(
+        error_information, original_exception=original_exception
+    )
 
     assert sanitized is not None
     assert sanitized["error_message"] == expected_error_message