diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index eefa739198..3124ae2697 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -5153,6 +5153,29 @@
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
+    "vertex_ai/mistral-small-2503@001": {
+        "max_tokens": 8191,
+        "max_input_tokens": 32000,
+        "max_output_tokens": 8191,
+        "input_cost_per_token": 0.000001,
+        "output_cost_per_token": 0.000003,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "supports_function_calling": true,
+        "mode": "chat",
+        "supports_tool_choice": true
+    },
+    "vertex_ai/mistral-small-2503": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 0.000001,
+        "output_cost_per_token": 0.000003,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_tool_choice": true
+    },
     "vertex_ai/jamba-1.5-mini@001": {
         "max_tokens": 256000,
         "max_input_tokens": 256000,
diff --git a/tests/local_testing/test_caching.py b/tests/local_testing/test_caching.py
index e4815f2023..30feb09f9d 100644
--- a/tests/local_testing/test_caching.py
+++ b/tests/local_testing/test_caching.py
@@ -1734,6 +1734,7 @@ def test_redis_semantic_cache_completion():
 # test_redis_cache_completion()
 
 
+@pytest.mark.flaky(reruns=3)
 @pytest.mark.asyncio
 async def test_redis_semantic_cache_acompletion():
     litellm.set_verbose = True
@@ -1761,6 +1762,8 @@ async def test_redis_semantic_cache_acompletion():
     )
     print(f"response1: {response1}")
 
+    await asyncio.sleep(2)
+
     response2 = await litellm.acompletion(
         model="gpt-3.5-turbo",
         messages=[