diff --git a/output/openapi/elasticsearch-openapi.json b/output/openapi/elasticsearch-openapi.json
index d50997116d..5408bb25e6 100644
--- a/output/openapi/elasticsearch-openapi.json
+++ b/output/openapi/elasticsearch-openapi.json
@@ -80108,7 +80108,7 @@
         "type": "object",
         "properties": {
           "requests_per_minute": {
-            "description": "The number of requests allowed per minute.",
+            "description": "The number of requests allowed per minute.\nBy default, the number of requests allowed per minute is set by each service as follows:\n\n* `alibabacloud-ai-search` service: `1000`\n* `anthropic` service: `50`\n* `azureaistudio` service: `240`\n* `azureopenai` service and task type `text_embedding`: `1440`\n* `azureopenai` service and task type `completion`: `120`\n* `cohere` service: `10000`\n* `elastic` service and task type `chat_completion`: `240`\n* `googleaistudio` service: `360`\n* `googlevertexai` service: `30000`\n* `hugging_face` service: `3000`\n* `jinaai` service: `2000`\n* `mistral` service: `240`\n* `openai` service and task type `text_embedding`: `3000`\n* `openai` service and task type `completion`: `500`\n* `voyageai` service: `2000`\n* `watsonxai` service: `120`",
             "type": "number"
           }
         }
diff --git a/output/openapi/elasticsearch-serverless-openapi.json b/output/openapi/elasticsearch-serverless-openapi.json
index b6d1cdce2e..a70fd8d30a 100644
--- a/output/openapi/elasticsearch-serverless-openapi.json
+++ b/output/openapi/elasticsearch-serverless-openapi.json
@@ -51188,7 +51188,7 @@
         "type": "object",
         "properties": {
           "requests_per_minute": {
-            "description": "The number of requests allowed per minute.",
+            "description": "The number of requests allowed per minute.\nBy default, the number of requests allowed per minute is set by each service as follows:\n\n* `alibabacloud-ai-search` service: `1000`\n* `anthropic` service: `50`\n* `azureaistudio` service: `240`\n* `azureopenai` service and task type `text_embedding`: `1440`\n* `azureopenai` service and task type `completion`: `120`\n* `cohere` service: `10000`\n* `elastic` service and task type `chat_completion`: `240`\n* `googleaistudio` service: `360`\n* `googlevertexai` service: `30000`\n* `hugging_face` service: `3000`\n* `jinaai` service: `2000`\n* `mistral` service: `240`\n* `openai` service and task type `text_embedding`: `3000`\n* `openai` service and task type `completion`: `500`\n* `voyageai` service: `2000`\n* `watsonxai` service: `120`",
             "type": "number"
           }
         }
diff --git a/output/schema/schema.json b/output/schema/schema.json
index 52f078c96c..754ed9f693 100644
--- a/output/schema/schema.json
+++ b/output/schema/schema.json
@@ -156479,13 +156479,14 @@
     },
     {
       "kind": "interface",
+      "description": "This setting helps to minimize the number of rate limit errors returned from the service.",
       "name": {
         "name": "RateLimitSetting",
         "namespace": "inference._types"
       },
       "properties": [
         {
-          "description": "The number of requests allowed per minute.",
+          "description": "The number of requests allowed per minute.\nBy default, the number of requests allowed per minute is set by each service as follows:\n\n* `alibabacloud-ai-search` service: `1000`\n* `anthropic` service: `50`\n* `azureaistudio` service: `240`\n* `azureopenai` service and task type `text_embedding`: `1440`\n* `azureopenai` service and task type `completion`: `120`\n* `cohere` service: `10000`\n* `elastic` service and task type `chat_completion`: `240`\n* `googleaistudio` service: `360`\n* `googlevertexai` service: `30000`\n* `hugging_face` service: `3000`\n* `jinaai` service: `2000`\n* `mistral` service: `240`\n* `openai` service and task type `text_embedding`: `3000`\n* `openai` service and task type `completion`: `500`\n* `voyageai` service: `2000`\n* `watsonxai` service: `120`",
           "name": "requests_per_minute",
           "required": false,
           "type": {
@@ -156497,7 +156498,7 @@
           }
         }
       ],
-      "specLocation": "inference/_types/Services.ts#L289-L294"
+      "specLocation": "inference/_types/Services.ts#L289-L315"
     },
     {
       "kind": "interface",
diff --git a/specification/inference/_types/Services.ts b/specification/inference/_types/Services.ts
index aa69b2bb22..23003780cc 100644
--- a/specification/inference/_types/Services.ts
+++ b/specification/inference/_types/Services.ts
@@ -286,9 +286,30 @@ export type ServiceSettings = UserDefinedValue
 
 export type TaskSettings = UserDefinedValue
 
+/**
+ * This setting helps to minimize the number of rate limit errors returned from the service.
+ */
 export class RateLimitSetting {
   /**
    * The number of requests allowed per minute.
+   * By default, the number of requests allowed per minute is set by each service as follows:
+   *
+   * * `alibabacloud-ai-search` service: `1000`
+   * * `anthropic` service: `50`
+   * * `azureaistudio` service: `240`
+   * * `azureopenai` service and task type `text_embedding`: `1440`
+   * * `azureopenai` service and task type `completion`: `120`
+   * * `cohere` service: `10000`
+   * * `elastic` service and task type `chat_completion`: `240`
+   * * `googleaistudio` service: `360`
+   * * `googlevertexai` service: `30000`
+   * * `hugging_face` service: `3000`
+   * * `jinaai` service: `2000`
+   * * `mistral` service: `240`
+   * * `openai` service and task type `text_embedding`: `3000`
+   * * `openai` service and task type `completion`: `500`
+   * * `voyageai` service: `2000`
+   * * `watsonxai` service: `120`
    */
   requests_per_minute?: integer
 }