diff --git a/tests/llm_translation/base_llm_unit_tests.py b/tests/llm_translation/base_llm_unit_tests.py
index 07083f4515..bd2838edb1 100644
--- a/tests/llm_translation/base_llm_unit_tests.py
+++ b/tests/llm_translation/base_llm_unit_tests.py
@@ -730,6 +730,8 @@ class BaseLLMChatTest(ABC):
                 second_response.choices[0].message.content is not None
                 or second_response.choices[0].message.tool_calls is not None
             )
+        except litellm.InternalServerError:
+            pytest.skip("Model is overloaded")
         except litellm.RateLimitError:
             pass
         except Exception as e:
diff --git a/tests/llm_translation/test_openai.py b/tests/llm_translation/test_openai.py
index 8c1444b849..2f10d42820 100644
--- a/tests/llm_translation/test_openai.py
+++ b/tests/llm_translation/test_openai.py
@@ -287,11 +287,14 @@ class TestOpenAIChatCompletion(BaseLLMChatTest):
         Context: https://github.com/openai/openai-python/issues/1921
         """
         base_completion_call_args = self.get_base_completion_call_args()
-        response = self.completion_function(
-            **base_completion_call_args,
-            messages=[{"role": "user", "content": "你好世界！\ud83e, ö"}],
-        )
-        assert response is not None
+        try:
+            response = self.completion_function(
+                **base_completion_call_args,
+                messages=[{"role": "user", "content": "你好世界！\ud83e, ö"}],
+            )
+            assert response is not None
+        except litellm.InternalServerError:
+            pytest.skip("Skipping test due to InternalServerError")
 
 
 def test_completion_bad_org():