diff --git a/output/schema/schema-serverless.json b/output/schema/schema-serverless.json
index 19430f8333..c82ab82184 100644
--- a/output/schema/schema-serverless.json
+++ b/output/schema/schema-serverless.json
@@ -4293,9 +4293,14 @@
           "visibility": "public"
         }
       },
-      "description": "Create an inference endpoint",
+      "description": "Create an inference endpoint.\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\nAfter creating the endpoint, wait for the model deployment to complete before using it.\nTo verify the deployment status, use the get trained model statistics API.\nLook for `\"state\": \"fully_allocated\"` in the response and ensure that the `\"allocation_count\"` matches the `\"target_allocation_count\"`.\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.\n\nIMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Mistral, Azure OpenAI, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face.\nFor built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models.\nHowever, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.",
       "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/master/put-inference-api.html",
       "name": "inference.put",
+      "privileges": {
+        "cluster": [
+          "manage_inference"
+        ]
+      },
       "request": {
         "name": "Request",
         "namespace": "inference.put"
@@ -24664,7 +24669,7 @@
           }
         }
       },
-      "description": "Create an inference endpoint",
+      "description": "Create an inference endpoint.\nWhen you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running.\nAfter creating the endpoint, wait for the model deployment to complete before using it.\nTo verify the deployment status, use the get trained model statistics API.\nLook for `\"state\": \"fully_allocated\"` in the response and ensure that the `\"allocation_count\"` matches the `\"target_allocation_count\"`.\nAvoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.\n\nIMPORTANT: The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Mistral, Azure OpenAI, Google AI Studio, Google Vertex AI, Anthropic, Watsonx.ai, or Hugging Face.\nFor built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models.\nHowever, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.",
       "inherits": {
         "type": {
           "name": "RequestBase",
@@ -24703,7 +24708,7 @@
         }
       ],
       "query": [],
-      "specLocation": "inference/put/PutRequest.ts#L25-L44"
+      "specLocation": "inference/put/PutRequest.ts#L25-L54"
     },
     {
       "body": {