diff --git a/litellm/litellm_core_utils/health_check_helpers.py b/litellm/litellm_core_utils/health_check_helpers.py
index 60e4b7495ed..69b12fea21b 100644
--- a/litellm/litellm_core_utils/health_check_helpers.py
+++ b/litellm/litellm_core_utils/health_check_helpers.py
@@ -283,7 +283,7 @@ class HealthCheckHelpers:
             ),
             "responses": lambda: litellm.aresponses(
                 **_filter_model_params(model_params=model_params),
-                input=prompt or "test",
+                input=[{"role": "user", "content": prompt or "test"}],
             ),
             "anthropic_messages": lambda: litellm.anthropic_messages(
                 **{
diff --git a/litellm/main.py b/litellm/main.py
index 37b290f51ba..8ec1eb9403a 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -8812,6 +8812,10 @@ async def ahealth_check(
         )
 
         model_params["cache"] = {"no-cache": True}  # don't used cached responses for making health check calls
+        # chatgpt provider uses the Responses API exclusively; default to "responses" so the
+        # health check doesn't send a Chat Completions payload that the backend rejects.
+        if mode is None and custom_llm_provider == "chatgpt":
+            mode = "responses"
         mode = mode or default_health_check_mode(
             requested_model=requested_model, model=model, custom_llm_provider=custom_llm_provider
         )