diff --git a/litellm/litellm_core_utils/token_counter.py b/litellm/litellm_core_utils/token_counter.py
index 4df944edba..fab2c1e76e 100644
--- a/litellm/litellm_core_utils/token_counter.py
+++ b/litellm/litellm_core_utils/token_counter.py
@@ -529,7 +529,7 @@ def _get_count_function(
                 encoding = tiktoken.get_encoding("cl100k_base")
 
             def count_tokens(text: str) -> int:
-                return len(encoding.encode(text))
+                return len(encoding.encode(text, disallowed_special=()))
 
         else:
             raise ValueError("Unsupported tokenizer type")
diff --git a/tests/test_litellm/litellm_core_utils/test_token_counter.py b/tests/test_litellm/litellm_core_utils/test_token_counter.py
index 71ee367bde..5d17ea3dc3 100644
--- a/tests/test_litellm/litellm_core_utils/test_token_counter.py
+++ b/tests/test_litellm/litellm_core_utils/test_token_counter.py
@@ -451,6 +451,7 @@ def test_img_url_token_counter(img_url):
 
 def test_token_encode_disallowed_special():
     encode(model="gpt-3.5-turbo", text="Hello, world! <|endoftext|>")
+    token_counter(model="gpt-3.5-turbo", text="Hello, world! <|endoftext|>")
 
 
 def test_token_counter():