diff --git a/litellm/llms/openai/common_utils.py b/litellm/llms/openai/common_utils.py
index 8bcecd35232..d8107a9ce90 100644
--- a/litellm/llms/openai/common_utils.py
+++ b/litellm/llms/openai/common_utils.py
@@ -22,7 +22,6 @@ from litellm.llms.custom_httpx.http_handler import (
     AsyncHTTPHandler,
     get_ssl_configuration,
 )
-from litellm.types.utils import LlmProviders
 
 
 class OpenAIError(BaseLLMException):
@@ -205,67 +204,30 @@ class BaseOpenAILLM:
         if litellm.aclient_session is not None:
             return litellm.aclient_session
 
-        # Use the global cached client system to prevent memory leaks (issue #14540)
-        # This routes through get_async_httpx_client() which provides TTL-based caching
-        from litellm.llms.custom_httpx.http_handler import get_async_httpx_client
+        # Get unified SSL configuration
+        ssl_config = get_ssl_configuration()
 
-        try:
-            # Get SSL config and include in params for proper cache key
-            ssl_config = get_ssl_configuration()
-            params = {"ssl_verify": ssl_config} if ssl_config is not None else {}
-            params["disable_aiohttp_transport"] = litellm.disable_aiohttp_transport
-
-            # Get a cached AsyncHTTPHandler which manages the httpx.AsyncClient
-            cached_handler = get_async_httpx_client(
-                llm_provider=LlmProviders.OPENAI,  # Cache key includes provider
-                params=params,  # Include SSL config in cache key
+        return httpx.AsyncClient(
+            verify=ssl_config,
+            transport=AsyncHTTPHandler._create_async_transport(
+                ssl_context=ssl_config
+                if isinstance(ssl_config, ssl.SSLContext)
+                else None,
+                ssl_verify=ssl_config if isinstance(ssl_config, bool) else None,
                 shared_session=shared_session,
-            )
-            # Return the underlying httpx client from the handler
-            return cached_handler.client
-        except (ImportError, AttributeError, KeyError) as e:
-            # Fallback to creating a client directly if caching system unavailable
-            # This preserves backwards compatibility
-            verbose_logger.debug(
-                f"Client caching unavailable ({type(e).__name__}), using direct client creation"
-            )
-            ssl_config = get_ssl_configuration()
-            return httpx.AsyncClient(
-                verify=ssl_config,
-                transport=AsyncHTTPHandler._create_async_transport(
-                    ssl_context=ssl_config
-                    if isinstance(ssl_config, ssl.SSLContext)
-                    else None,
-                    ssl_verify=ssl_config if isinstance(ssl_config, bool) else None,
-                    shared_session=shared_session,
-                ),
-                follow_redirects=True,
-            )
+            ),
+            follow_redirects=True,
+        )
 
     @staticmethod
     def _get_sync_http_client() -> Optional[httpx.Client]:
         if litellm.client_session is not None:
             return litellm.client_session
 
-        # Use the global cached client system to prevent memory leaks (issue #14540)
-        from litellm.llms.custom_httpx.http_handler import _get_httpx_client
+        # Get unified SSL configuration
+        ssl_config = get_ssl_configuration()
 
-        try:
-            # Get SSL config and include in params for proper cache key
-            ssl_config = get_ssl_configuration()
-            params = {"ssl_verify": ssl_config} if ssl_config is not None else None
-
-            # Get a cached HTTPHandler which manages the httpx.Client
-            cached_handler = _get_httpx_client(params=params)
-            # Return the underlying httpx client from the handler
-            return cached_handler.client
-        except (ImportError, AttributeError, KeyError) as e:
-            # Fallback to creating a client directly if caching system unavailable
-            verbose_logger.debug(
-                f"Client caching unavailable ({type(e).__name__}), using direct client creation"
-            )
-            ssl_config = get_ssl_configuration()
-            return httpx.Client(
-                verify=ssl_config,
-                follow_redirects=True,
-            )
+        return httpx.Client(
+            verify=ssl_config,
+            follow_redirects=True,
+        )
diff --git a/tests/test_litellm/llms/test_lifecycle_fix.py b/tests/test_litellm/llms/test_lifecycle_fix.py
new file mode 100644
index 00000000000..7b1876a3331
--- /dev/null
+++ b/tests/test_litellm/llms/test_lifecycle_fix.py
@@ -0,0 +1,46 @@
+"""
+Verifies that the httpx client used by AsyncOpenAI is NOT closed
+when AsyncHTTPHandler instances are garbage collected.
+"""
+import asyncio
+import gc
+import httpx
+from litellm.llms.openai.common_utils import BaseOpenAILLM
+from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler
+
+
+async def test_httpx_client_not_closed_by_handler_gc():
+    """
+    Before the fix: _get_async_http_client() returned handler.client,
+    so when handler was GC'd its __del__ closed the client.
+    After the fix: returns a standalone httpx.AsyncClient, no handler involved.
+    """
+    # Get the client the same way AsyncOpenAI would
+    client = BaseOpenAILLM._get_async_http_client()
+    assert isinstance(client, httpx.AsyncClient)
+
+    # Simulate what the old code did: create an AsyncHTTPHandler and GC it
+    handler = AsyncHTTPHandler()
+    handler_client = handler.client
+    del handler
+    gc.collect()
+
+    # The client from _get_async_http_client should still be open
+    # because it's NOT tied to any AsyncHTTPHandler
+    assert not client.is_closed, "Client was closed prematurely!"
+
+    # Verify it can actually send (build a request without sending)
+    try:
+        req = client.build_request("GET", "https://example.com")
+        print("PASS: Client is still usable after handler GC")
+    except RuntimeError as e:
+        if "closed" in str(e):
+            print(f"FAIL: {e}")
+            raise
+        raise
+
+    await client.aclose()
+    print("All checks passed!")
+
+
+asyncio.run(test_httpx_client_not_closed_by_handler_gc())