diff --git a/tests/test_litellm/responses/test_responses_api_request_body.py b/tests/test_litellm/responses/test_responses_api_request_body.py
index 38dc61c5aa0..ea5eb3afe9a 100644
--- a/tests/test_litellm/responses/test_responses_api_request_body.py
+++ b/tests/test_litellm/responses/test_responses_api_request_body.py
@@ -12,6 +12,7 @@ import httpx
 import pytest
 
 import litellm
+from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler
 
 
 def _expected_dir() -> Path:
@@ -384,22 +385,21 @@ async def test_aresponses_strips_responses_routing_prefix_from_openai_model(mode
     /v1/responses and via the /v1/messages adapter (which passes responses/<model>
     with custom_llm_provider="openai"), so both shapes must hit OpenAI as <model>.
     """
-    with patch(
-        "litellm.llms.custom_httpx.http_handler.AsyncHTTPHandler.post",
-        new_callable=AsyncMock,
-    ) as mock_post:
-        mock_post.return_value = MockResponse(_minimal_responses_api_payload("resp_prefix_test", "gpt-5.6"), 200)
+    injected_client = AsyncHTTPHandler()
+    mock_post = AsyncMock(return_value=MockResponse(_minimal_responses_api_payload("resp_prefix_test", "gpt-5.6"), 200))
+    injected_client.post = mock_post
 
-        await litellm.aresponses(
-            model=model,
-            custom_llm_provider=custom_llm_provider,
-            input="ping",
-            api_key="sk-test",
-        )
+    await litellm.aresponses(
+        model=model,
+        custom_llm_provider=custom_llm_provider,
+        input="ping",
+        api_key="sk-test",
+        client=injected_client,
+    )
 
-        mock_post.assert_called_once()
-        assert mock_post.call_args.kwargs["url"].endswith("/responses")
-        assert mock_post.call_args.kwargs["json"]["model"] == "gpt-5.6"
+    mock_post.assert_called_once()
+    assert mock_post.call_args.kwargs["url"].endswith("/responses")
+    assert mock_post.call_args.kwargs["json"]["model"] == "gpt-5.6"
 
 
 @pytest.mark.asyncio