diff --git a/litellm/passthrough/main.py b/litellm/passthrough/main.py
index c06297ec15b..8b20406397b 100644
--- a/litellm/passthrough/main.py
+++ b/litellm/passthrough/main.py
@@ -108,7 +108,7 @@ async def allm_passthrough_route(
     json: Optional[Any] = None,
     params: Optional[QueryParamTypes] = None,
     cookies: Optional[CookieTypes] = None,
-    http_client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
+    client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
     **kwargs,
 ) -> Union[httpx.Response, AsyncIterator[bytes]]:
     """
@@ -154,7 +154,7 @@ async def allm_passthrough_route(
             json=json,
             params=params,
             cookies=cookies,
-            http_client=http_client,
+            client=client,
             **kwargs,
         )
 
@@ -234,7 +234,7 @@ def llm_passthrough_route(
     json: Optional[Any] = None,
     params: Optional[QueryParamTypes] = None,
     cookies: Optional[CookieTypes] = None,
-    http_client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
+    client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
     **kwargs,
 ) -> Union[
     httpx.Response,
@@ -256,11 +256,11 @@ def llm_passthrough_route(
 
     _is_async = allm_passthrough_route
 
-    if http_client is None:
+    if client is None:
         if _is_async:
-            http_client = litellm.module_level_aclient
+            client = litellm.module_level_aclient
         else:
-            http_client = litellm.module_level_client
+            client = litellm.module_level_client
 
     litellm_logging_obj = cast("LiteLLMLoggingObj", kwargs.get("litellm_logging_obj"))
 
@@ -342,7 +342,7 @@ def llm_passthrough_route(
     if json and isinstance(json, dict) and "model" in json:
         json["model"] = model
 
-    request = http_client.client.build_request(
+    request = client.client.build_request(
         method=method,
         url=updated_url,
         content=signed_json_body if signed_json_body is not None else content,
@@ -379,7 +379,7 @@ def llm_passthrough_route(
         if _is_async:
             # Return the coroutine to be awaited by the caller
             return _async_passthrough_request(
-                client=http_client,
+                client=client,
                 request=request,
                 is_streaming_request=is_streaming_request,
                 litellm_logging_obj=litellm_logging_obj,
@@ -387,7 +387,7 @@ def llm_passthrough_route(
             )
         else:
             # Sync path - client.client.send returns Response directly
-            response: httpx.Response = http_client.client.send(request=request, stream=is_streaming_request)  # type: ignore
+            response: httpx.Response = client.client.send(request=request, stream=is_streaming_request)  # type: ignore
             response.raise_for_status()
 
             if (
diff --git a/tests/pass_through_tests/test_hosted_vllm_passthrough.py b/tests/pass_through_tests/test_hosted_vllm_passthrough.py
index e8d4c0d2ef0..272b4e1bb00 100644
--- a/tests/pass_through_tests/test_hosted_vllm_passthrough.py
+++ b/tests/pass_through_tests/test_hosted_vllm_passthrough.py
@@ -63,7 +63,7 @@ async def test_allm_passthrough_route_with_hosted_vllm_model_does_not_raise():
                     "model": "anything",  # will be replaced internally with normalized model
                     "messages": [{"role": "user", "content": "Hello"}],
                 },
-                http_client=client,
+                client=client,
             )
 
             # Then it should not raise and return a successful httpx.Response
diff --git a/tests/test_litellm/passthrough/test_passthrough_main.py b/tests/test_litellm/passthrough/test_passthrough_main.py
index adcca96271e..3600aeed59e 100644
--- a/tests/test_litellm/passthrough/test_passthrough_main.py
+++ b/tests/test_litellm/passthrough/test_passthrough_main.py
@@ -40,7 +40,7 @@ def test_llm_passthrough_route():
                 "model": "my-custom-model",
                 "messages": [{"role": "user", "content": "Hello, world!"}],
             },
-            http_client=client,
+            client=client,
         )
 
         mock_post.call_args.kwargs[
@@ -94,7 +94,7 @@ def test_bedrock_application_inference_profile_url_encoding():
             endpoint="model/arn:aws:bedrock:us-east-1:123456789123:application-inference-profile/r742sbn2zckd/converse",
             method="POST",
             custom_llm_provider="bedrock",
-            http_client=client,
+            client=client,
             litellm_logging_obj=mock_logging_obj,
         )
 
@@ -152,7 +152,7 @@ def test_bedrock_non_application_inference_profile_no_encoding():
             endpoint="model/anthropic.claude-3-sonnet-20240229-v1:0/converse",
             method="POST",
             custom_llm_provider="bedrock",
-            http_client=client,
+            client=client,
             litellm_logging_obj=mock_logging_obj,
         )
 
@@ -511,7 +511,7 @@ def test_azure_with_custom_api_base_and_key():
                 "model": "gpt-4.1",
                 "messages": [{"role": "user", "content": "Hello!"}],
             },
-            http_client=client,
+            client=client,
             litellm_logging_obj=mock_logging_obj,
         )
 
@@ -592,7 +592,7 @@ def test_content_param_forwarded_to_build_request():
             content=raw_content,
             data=None,
             json=None,
-            http_client=client,
+            client=client,
             litellm_logging_obj=mock_logging_obj,
         )
 
@@ -717,7 +717,7 @@ async def test_allm_passthrough_route_429_streaming_raises():
                 api_base="https://my-azure.openai.azure.com",
                 api_key="fake-azure-key",
                 json={"model": "gpt-4", "input": "hello", "stream": True},
-                http_client=async_client,
+                client=async_client,
                 litellm_logging_obj=mock_logging_obj,
             )