diff --git a/litellm/integrations/langsmith.py b/litellm/integrations/langsmith.py
index afe8be28f5..81db798ae8 100644
--- a/litellm/integrations/langsmith.py
+++ b/litellm/integrations/langsmith.py
@@ -8,6 +8,7 @@ from datetime import datetime
 from typing import Any, List, Optional, Union
 
 import dotenv  # type: ignore
+import httpx
 import requests  # type: ignore
 from pydantic import BaseModel  # type: ignore
 
@@ -59,7 +60,9 @@ class LangsmithLogger(CustomLogger):
         self.langsmith_base_url = os.getenv(
             "LANGSMITH_BASE_URL", "https://api.smith.langchain.com"
         )
-        self.async_httpx_client = AsyncHTTPHandler()
+        self.async_httpx_client = AsyncHTTPHandler(
+            timeout=httpx.Timeout(timeout=600.0, connect=5.0)
+        )
 
     def _prepare_log_data(self, kwargs, response_obj, start_time, end_time):
         import datetime
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 2fc6a5771d..8803940fbb 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -1820,26 +1820,6 @@
         "supports_vision": true,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
     },
-    "medlm-medium": {
-        "max_tokens": 8192,
-        "max_input_tokens": 32768,
-        "max_output_tokens": 8192,
-        "input_cost_per_character": 0.0000005,
-        "output_cost_per_character": 0.000001,
-        "litellm_provider": "vertex_ai-language-models",
-        "mode": "chat",
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
-    "medlm-large": {
-        "max_tokens": 1024,
-        "max_input_tokens": 8192,
-        "max_output_tokens": 1024,
-        "input_cost_per_character": 0.000005,
-        "output_cost_per_character": 0.000015,
-        "litellm_provider": "vertex_ai-language-models",
-        "mode": "chat",
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
-    },
     "vertex_ai/claude-3-sonnet@20240229": {
         "max_tokens": 4096,
         "max_input_tokens": 200000,
diff --git a/litellm/tests/test_langsmith.py b/litellm/tests/test_langsmith.py
index f69c964a13..96fdbc2a4a 100644
--- a/litellm/tests/test_langsmith.py
+++ b/litellm/tests/test_langsmith.py
@@ -20,13 +20,11 @@ verbose_logger.setLevel(logging.DEBUG)
 litellm.set_verbose = True
 import time
 
-test_langsmith_logger = LangsmithLogger()
-
 
 @pytest.mark.asyncio()
-async def test_langsmith_logging():
+async def test_async_langsmith_logging():
     try:
-
+        test_langsmith_logger = LangsmithLogger()
         run_id = str(uuid.uuid4())
         litellm.set_verbose = True
         litellm.callbacks = ["langsmith"]
@@ -84,7 +82,7 @@ async def test_langsmith_logging():
 # test_langsmith_logging()
 
 
-def test_langsmith_logging_with_metadata():
+def test_async_langsmith_logging_with_metadata():
     try:
         litellm.success_callback = ["langsmith"]
         litellm.set_verbose = True
@@ -104,8 +102,9 @@ def test_langsmith_logging_with_metadata():
 
 @pytest.mark.parametrize("sync_mode", [False, True])
 @pytest.mark.asyncio
-async def test_langsmith_logging_with_streaming_and_metadata(sync_mode):
+async def test_async_langsmith_logging_with_streaming_and_metadata(sync_mode):
     try:
+        test_langsmith_logger = LangsmithLogger()
         litellm.success_callback = ["langsmith"]
         litellm.set_verbose = True
         run_id = str(uuid.uuid4())