diff --git a/litellm/proxy/health_check.py b/litellm/proxy/health_check.py
index 652800b4aef..488467e1b99 100644
--- a/litellm/proxy/health_check.py
+++ b/litellm/proxy/health_check.py
@@ -401,7 +401,7 @@ def _resolve_health_check_max_tokens(
     3. For non-wildcard reasoning routes: BACKGROUND_HEALTH_CHECK_MAX_TOKENS_REASONING
        from env (if set)
     4. BACKGROUND_HEALTH_CHECK_MAX_TOKENS (global, any route including wildcards)
-    5. Non-wildcard default: 5
+    5. Non-wildcard default: 16
     6. Wildcard and nothing from (1)(4): leave unset (caller omits max_tokens)
     """
     explicit = model_info.get("health_check_max_tokens", None)
@@ -432,7 +432,7 @@ def _resolve_health_check_max_tokens(
         return int(BACKGROUND_HEALTH_CHECK_MAX_TOKENS)
 
     if not is_wildcard:
-        return 16  # OpenAI GPT-5 models require max_output_tokens >= 16
+        return 16
 
     return None
 
diff --git a/tests/test_litellm/proxy/test_health_check_max_tokens.py b/tests/test_litellm/proxy/test_health_check_max_tokens.py
index db82f11c5cc..e56eb9bfdd6 100644
--- a/tests/test_litellm/proxy/test_health_check_max_tokens.py
+++ b/tests/test_litellm/proxy/test_health_check_max_tokens.py
@@ -49,8 +49,7 @@ async def test_update_litellm_params_max_tokens_wildcard():
 
     updated_params = _update_litellm_params_for_health_check(model_info, litellm_params)
 
-    # Should not be set to 1
-    assert "max_tokens" not in updated_params or updated_params["max_tokens"] != 1
+    assert "max_tokens" not in updated_params
 
 
 @pytest.mark.asyncio