diff --git a/specification/cognitiveservices/OpenAI.Inference/models/completions/chat_completions.tsp b/specification/cognitiveservices/OpenAI.Inference/models/completions/chat_completions.tsp
index 6733465d4adb..913808db5f30 100644
--- a/specification/cognitiveservices/OpenAI.Inference/models/completions/chat_completions.tsp
+++ b/specification/cognitiveservices/OpenAI.Inference/models/completions/chat_completions.tsp
@@ -248,6 +248,7 @@ model ChatChoice {
   finishReason: CompletionsFinishReason | null;
 
   // Note: this property is currently speculative via observation and not yet documented anywhere.
+
   @doc("""
   The reason the model stopped generating tokens, together with any applicable details.
   This structured representation replaces 'finish_reason' for some models.
@@ -303,6 +304,9 @@ model ChatCompletions {
     """)
   choices: ChatChoice[];
 
+  @doc("The model name used for this completions request.")
+  `model`?: string;
+
   @doc("""
   Content filtering results for zero or more prompts in the request. In a streaming request,
   results for different prompts may arrive at different times or in different orders.
diff --git a/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2023-06-01-preview/generated.json b/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2023-06-01-preview/generated.json
index 98e10aafb929..70be8058d964 100644
--- a/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2023-06-01-preview/generated.json
+++ b/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2023-06-01-preview/generated.json
@@ -504,6 +504,10 @@
           },
           "x-ms-identifiers": []
         },
+        "model": {
+          "type": "string",
+          "description": "The model name used for this completions request."
+        },
         "prompt_filter_results": {
           "type": "array",
           "description": "Content filtering results for zero or more prompts in the request. In a streaming request,\nresults for different prompts may arrive at different times or in different orders.",
diff --git a/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2023-07-01-preview/generated.json b/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2023-07-01-preview/generated.json
index 79ee9f7440d6..ee96decf5d69 100644
--- a/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2023-07-01-preview/generated.json
+++ b/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2023-07-01-preview/generated.json
@@ -504,6 +504,10 @@
           },
           "x-ms-identifiers": []
         },
+        "model": {
+          "type": "string",
+          "description": "The model name used for this completions request."
+        },
         "prompt_filter_results": {
           "type": "array",
           "description": "Content filtering results for zero or more prompts in the request. In a streaming request,\nresults for different prompts may arrive at different times or in different orders.",
diff --git a/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-02-15-preview/generated.json b/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-02-15-preview/generated.json
index 26bb7a06e7e5..89c303650ab5 100644
--- a/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-02-15-preview/generated.json
+++ b/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-02-15-preview/generated.json
@@ -1795,6 +1795,10 @@
           },
           "x-ms-identifiers": []
         },
+        "model": {
+          "type": "string",
+          "description": "The model name used for this completions request."
+        },
         "prompt_filter_results": {
           "type": "array",
           "description": "Content filtering results for zero or more prompts in the request. In a streaming request,\nresults for different prompts may arrive at different times or in different orders.",
diff --git a/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-03-01-preview/generated.json b/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-03-01-preview/generated.json
index 85e396950a12..ab4c82c48748 100644
--- a/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-03-01-preview/generated.json
+++ b/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-03-01-preview/generated.json
@@ -1795,6 +1795,10 @@
           },
           "x-ms-identifiers": []
         },
+        "model": {
+          "type": "string",
+          "description": "The model name used for this completions request."
+        },
         "prompt_filter_results": {
           "type": "array",
           "description": "Content filtering results for zero or more prompts in the request. In a streaming request,\nresults for different prompts may arrive at different times or in different orders.",
diff --git a/specification/cognitiveservices/data-plane/AzureOpenAI/inference/stable/2023-05-15/generated.json b/specification/cognitiveservices/data-plane/AzureOpenAI/inference/stable/2023-05-15/generated.json
index d2a02c008396..4025b89cae3a 100644
--- a/specification/cognitiveservices/data-plane/AzureOpenAI/inference/stable/2023-05-15/generated.json
+++ b/specification/cognitiveservices/data-plane/AzureOpenAI/inference/stable/2023-05-15/generated.json
@@ -325,6 +325,10 @@
           },
           "x-ms-identifiers": []
         },
+        "model": {
+          "type": "string",
+          "description": "The model name used for this completions request."
+        },
         "usage": {
           "$ref": "#/definitions/CompletionsUsage",
           "description": "Usage information for tokens processed and generated as part of this completions operation."