diff --git a/docs/my-website/docs/proxy/config_settings.md b/docs/my-website/docs/proxy/config_settings.md
index 528a5c109035..11cec01fdee4 100644
--- a/docs/my-website/docs/proxy/config_settings.md
+++ b/docs/my-website/docs/proxy/config_settings.md
@@ -1032,6 +1032,7 @@ router_settings:
 | SENDGRID_SENDER_EMAIL | Email address used as the sender in SendGrid email transactions 
 | SPEND_LOGS_URL | URL for retrieving spend logs
 | SPEND_LOG_CLEANUP_BATCH_SIZE | Number of logs deleted per batch during cleanup. Default is 1000
+| STALE_OBJECT_CLEANUP_BATCH_SIZE | Max number of stale managed objects updated per cleanup cycle. Default is 1000
 | SSL_CERTIFICATE | Path to the SSL certificate file
 | SSL_ECDH_CURVE | ECDH curve for SSL/TLS key exchange (e.g., 'X25519' to disable PQC).
 | SSL_SECURITY_LEVEL | [BETA] Security level for SSL/TLS connections. E.g. `DEFAULT@SECLEVEL=1`
diff --git a/enterprise/litellm_enterprise/proxy/common_utils/check_responses_cost.py b/enterprise/litellm_enterprise/proxy/common_utils/check_responses_cost.py
index 54fbc7abcc59..dc0168683c80 100644
--- a/enterprise/litellm_enterprise/proxy/common_utils/check_responses_cost.py
+++ b/enterprise/litellm_enterprise/proxy/common_utils/check_responses_cost.py
@@ -11,6 +11,7 @@
 from litellm.constants import (
     MANAGED_OBJECT_STALENESS_CUTOFF_DAYS,
     MAX_OBJECTS_PER_POLL_CYCLE,
+    STALE_OBJECT_CLEANUP_BATCH_SIZE,
 )
 
 if TYPE_CHECKING:
@@ -32,21 +33,49 @@ def __init__(
         self.prisma_client: PrismaClient = prisma_client
         self.llm_router: Router = llm_router
 
+    async def _expire_stale_rows(
+        self, cutoff: datetime, batch_size: int
+    ) -> int:
+        """Execute the bounded UPDATE that marks stale rows as 'stale_expired'.
+
+        Isolated so it can be swapped / mocked in tests without touching the
+        orchestration logic in ``_cleanup_stale_managed_objects``.
+
+        Uses PostgreSQL syntax (``$1::timestamptz``, ``LIMIT``, double-quoted
+        identifiers) which is the only dialect the proxy supports — every
+        ``schema.prisma`` in the repo sets ``provider = "postgresql"``.
+        Same pattern as ``spend_log_cleanup.py``.
+        """
+        return await self.prisma_client.db.execute_raw(
+            """
+            UPDATE "LiteLLM_ManagedObjectTable"
+            SET "status" = 'stale_expired'
+            WHERE "id" IN (
+                SELECT "id" FROM "LiteLLM_ManagedObjectTable"
+                WHERE "file_purpose" = 'response'
+                AND "status" NOT IN ('completed', 'complete', 'failed', 'expired', 'cancelled', 'stale_expired')
+                AND "created_at" < $1::timestamptz
+                ORDER BY "created_at" ASC
+                LIMIT $2
+            )
+            """,
+            cutoff,
+            batch_size,
+        )
+
     async def _cleanup_stale_managed_objects(self) -> None:
         """
         Mark managed objects older than MANAGED_OBJECT_STALENESS_CUTOFF_DAYS days
         in non-terminal states as 'stale_expired'. These will never complete and
         should not be polled.
+
+        Runs as a single DB query with a subquery LIMIT so no rows are loaded
+        into Python memory. Processes at most STALE_OBJECT_CLEANUP_BATCH_SIZE
+        rows per invocation to avoid overwhelming the DB when there is a large
+        backlog.
         """
         cutoff = datetime.now(timezone.utc) - timedelta(days=MANAGED_OBJECT_STALENESS_CUTOFF_DAYS)
-        result = await self.prisma_client.db.litellm_managedobjecttable.update_many(
-            where={
-                "file_purpose": "response",
-                "status": {"not_in": ["completed", "complete", "failed", "expired", "cancelled", "stale_expired"]},
-                "created_at": {"lt": cutoff},
-            },
-            data={"status": "stale_expired"},
-        )
+        result = await self._expire_stale_rows(cutoff, STALE_OBJECT_CLEANUP_BATCH_SIZE)
         if result > 0:
             verbose_proxy_logger.warning(
                 f"CheckResponsesCost: marked {result} stale managed objects "
diff --git a/litellm/constants.py b/litellm/constants.py
index 1af53b2dae08..28c6c0cc0e39 100644
--- a/litellm/constants.py
+++ b/litellm/constants.py
@@ -1367,6 +1367,9 @@
 MANAGED_OBJECT_STALENESS_CUTOFF_DAYS = max(
     1, int(os.getenv("MANAGED_OBJECT_STALENESS_CUTOFF_DAYS", 7))
 )
+STALE_OBJECT_CLEANUP_BATCH_SIZE = max(
+    1, int(os.getenv("STALE_OBJECT_CLEANUP_BATCH_SIZE", 1000))
+)
 # Set PROXY_BATCH_POLLING_ENABLED=false to disable the CheckBatchCost and
 # CheckResponsesCost background polling jobs entirely (e.g. to avoid DB load on
 # installations with large numbers of stale managed objects).
diff --git a/tests/local_testing/test_embedding.py b/tests/local_testing/test_embedding.py
index c43cad78b1e7..3f1a397ebcbe 100644
--- a/tests/local_testing/test_embedding.py
+++ b/tests/local_testing/test_embedding.py
@@ -373,35 +373,6 @@ def test_openai_azure_embedding_optional_arg():
 # test_openai_embedding()
 
 
-@pytest.mark.parametrize(
-    "model, api_base",
-    [
-        ("embed-english-v2.0", None),
-    ],
-)
-@pytest.mark.parametrize("sync_mode", [True, False])
-@pytest.mark.asyncio
-async def test_cohere_embedding(sync_mode, model, api_base):
-    try:
-        # litellm.set_verbose=True
-        data = {
-            "model": model,
-            "input": ["good morning from litellm", "this is another item"],
-            "input_type": "search_query",
-            "api_base": api_base,
-        }
-        if sync_mode:
-            response = embedding(**data)
-        else:
-            response = await litellm.aembedding(**data)
-
-        print(f"response:", response)
-
-        assert isinstance(response.usage, litellm.Usage)
-    except Exception as e:
-        pytest.fail(f"Error occurred: {e}")
-
-
 # test_cohere_embedding()