diff --git a/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py b/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py
index e15d449287..43f0fa1dbe 100644
--- a/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py
+++ b/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py
@@ -172,7 +172,7 @@ async def _call_messages(
 ) -> Tuple[int, Optional[Exception]]:
     kwargs = _build_messages_kwargs(model, effort)
     try:
-        await litellm.messages.acreate(**kwargs)
+        await litellm.anthropic_messages(**kwargs)
         return 200, None
     except BadRequestError as exc:
         return 400, exc
diff --git a/tests/test_litellm/interactions/test_openapi_compliance.py b/tests/test_litellm/interactions/test_openapi_compliance.py
index 11d61d4c82..ce74bf150a 100644
--- a/tests/test_litellm/interactions/test_openapi_compliance.py
+++ b/tests/test_litellm/interactions/test_openapi_compliance.py
@@ -157,15 +157,17 @@ class TestResponseCompliance:
         # Check CreateModelInteractionParams which includes output fields
         schema = spec_dict["components"]["schemas"]["CreateModelInteractionParams"]
 
-        # Output fields (readOnly). Google renamed `outputs` → `steps` in the
-        # upstream spec; keep this list aligned with the live schema.
+        # Output fields (readOnly). Google's live spec has churned through
+        # both `outputs` and `steps` for the per-turn output array and at the
+        # moment carries neither -- only the stable response-level fields
+        # below are guaranteed. Re-add the per-turn key once upstream
+        # stabilizes on a name.
         output_fields = [
             "id",
             "status",
             "created",
             "updated",
             "role",
-            "steps",
             "usage",
         ]