diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
index f3a91abc830..f4a95dfce30 100644
--- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
+++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
@@ -301,7 +301,6 @@ def test_fully_accounted_tokens_no_change():
  
 def test_double_counting_still_handled():
     """
-    Scenario: xAI-style double counting where text_tokens includes cached_tokens.
     Provider reports:
         - prompt_tokens = 500
         - text_tokens = 500 (includes cached)