diff --git a/litellm/tests/test_caching.py b/litellm/tests/test_caching.py
index 78c3c86a70..dd6a57dbd6 100644
--- a/litellm/tests/test_caching.py
+++ b/litellm/tests/test_caching.py
@@ -1,4 +1,5 @@
 import sys, os
+import time
 import traceback
 from dotenv import load_dotenv
 
@@ -36,7 +37,7 @@ def test_gpt_cache():
         cache_key = last_content_without_prompt_val + data["model"]
         print("cache_key", cache_key)
         return cache_key
-        
+
 
     cache.init(pre_func=pre_cache_func)
     cache.set_openai_key()
@@ -46,12 +47,12 @@ def test_gpt_cache():
     response2 = completion(model="gpt-3.5-turbo", messages=messages)
     response3 = completion(model="command-nightly", messages=messages)
 
-    if response1["choices"] != response2["choices"]: # same models should cache 
+    if response1["choices"] != response2["choices"]: # same models should cache
         print(f"response1: {response1}")
         print(f"response2: {response2}")
         pytest.fail(f"Error occurred:")
 
-    if response3["choices"] == response2["choices"]: # different models, don't cache 
+    if response3["choices"] == response2["choices"]: # different models, don't cache
         # if models are different, it should not return cached response
         print(f"response2: {response2}")
         print(f"response3: {response3}")
@@ -124,9 +125,9 @@ def test_embedding_caching():
     embedding2 = embedding(model="text-embedding-ada-002", input=text_to_embed, caching=True)
     end_time = time.time()
     print(f"Embedding 2 response time: {end_time - start_time} seconds")
-    
+
     litellm.cache = None
-    assert end_time - start_time <= 0.1 # ensure 2nd response comes in in under 0.1 s 
+    assert end_time - start_time <= 0.1 # ensure 2nd response comes in in under 0.1 s
     if embedding2['data'][0]['embedding'] != embedding1['data'][0]['embedding']:
         print(f"embedding1: {embedding1}")
         print(f"embedding2: {embedding2}")
@@ -178,14 +179,14 @@ def test_embedding_caching_azure():
     )
     end_time = time.time()
     print(f"Embedding 2 response time: {end_time - start_time} seconds")
-    
+
     litellm.cache = None
-    assert end_time - start_time <= 0.1 # ensure 2nd response comes in in under 0.1 s 
+    assert end_time - start_time <= 0.1 # ensure 2nd response comes in in under 0.1 s
     if embedding2['data'][0]['embedding'] != embedding1['data'][0]['embedding']:
         print(f"embedding1: {embedding1}")
         print(f"embedding2: {embedding2}")
         pytest.fail("Error occurred: Embedding caching failed")
-    
+
     os.environ['AZURE_API_VERSION'] = api_version
     os.environ['AZURE_API_BASE'] = api_base
     os.environ['AZURE_API_KEY'] = api_key
@@ -279,11 +280,11 @@ def test_redis_cache_completion():
 
     def set_cache(key, value):
         local_cache[key] = value
-    
+
     def get_cache(key):
         if key in local_cache:
             return local_cache[key]
-    
+
     litellm.cache.cache.set_cache = set_cache
     litellm.cache.cache.get_cache = get_cache
 
@@ -322,11 +323,11 @@ def test_custom_redis_cache_with_key():
 
     def set_cache(key, value):
         local_cache[key] = value
-    
+
     def get_cache(key):
         if key in local_cache:
             return local_cache[key]
-    
+
     litellm.cache.cache.set_cache = set_cache
     litellm.cache.cache.get_cache = get_cache
 
@@ -335,16 +336,16 @@ def test_custom_redis_cache_with_key():
     response1 = completion(model="gpt-3.5-turbo", messages=messages, temperature=1, caching=True)
     response2 = completion(model="gpt-3.5-turbo", messages=messages, temperature=1, caching=True)
     response3 = completion(model="gpt-3.5-turbo", messages=messages, temperature=1, caching=False)
-    
+
     print(f"response1: {response1}")
     print(f"response2: {response2}")
     print(f"response3: {response3}")
 
     if response3['choices'][0]['message']['content'] == response2['choices'][0]['message']['content']:
-        pytest.fail(f"Error occurred:")        
+        pytest.fail(f"Error occurred:")
     litellm.cache = None
 
-test_custom_redis_cache_with_key()
+# test_custom_redis_cache_with_key()
 
 def test_hosted_cache():
     litellm.cache = Cache(type="hosted") # use api.litellm.ai for caching
@@ -364,3 +365,20 @@ def test_hosted_cache():
 
 # test_hosted_cache()
 
+
+def test_redis_cache_with_ttl():
+    cache = Cache(type="redis", host=os.environ['REDIS_HOST'], port=os.environ['REDIS_PORT'], password=os.environ['REDIS_PASSWORD'])
+    cache.add_cache(cache_key="test_key", result="test_value", ttl=1)
+    cached_value = cache.get_cache(cache_key="test_key")
+    assert cached_value == "test_value"
+    time.sleep(2)
+    assert cache.get_cache(cache_key="test_key") is None
+
+
+def test_in_memory_cache_with_ttl():
+    cache = Cache(type="local")
+    cache.add_cache(cache_key="test_key", result="test_value", ttl=1)
+    cached_value = cache.get_cache(cache_key="test_key")
+    assert cached_value == "test_value"
+    time.sleep(2)
+    assert cache.get_cache(cache_key="test_key") is None