diff --git a/litellm/litellm_core_utils/exception_mapping_utils.py b/litellm/litellm_core_utils/exception_mapping_utils.py
index f8c786daef3..056522e2a64 100644
--- a/litellm/litellm_core_utils/exception_mapping_utils.py
+++ b/litellm/litellm_core_utils/exception_mapping_utils.py
@@ -77,6 +77,7 @@ class ExceptionCheckers:
             "model's maximum context limit",
             "is longer than the model's context length",
             "input tokens exceed the configured limit",
+            "`inputs` tokens + `max_new_tokens` must be",
         ]
         for substring in known_exception_substrings:
             if substring in _error_str_lowercase:
diff --git a/tests/test_litellm/litellm_core_utils/test_exception_mapping_utils.py b/tests/test_litellm/litellm_core_utils/test_exception_mapping_utils.py
index d7da7592870..d59e52d965e 100644
--- a/tests/test_litellm/litellm_core_utils/test_exception_mapping_utils.py
+++ b/tests/test_litellm/litellm_core_utils/test_exception_mapping_utils.py
@@ -36,6 +36,10 @@ context_window_test_cases = [
         "Input tokens exceed the configured limit of 272000 tokens. Your messages resulted in 509178 tokens. Please reduce the length of the messages.",
         True,
     ),
+    (
+        "`inputs` tokens + `max_new_tokens` must be <= 4096",
+        True,
+    ),
     # Test case insensitivity
     ("ERROR: THIS MODEL'S MAXIMUM CONTEXT LENGTH IS 1024.", True),
     # Negative cases (should return False)