@@ -4657,9 +4657,9 @@ Represents a completion response from the API. Note: both the streamed and non-s
 | function_call | string or [chatCompletionFunctionCallOption](#chatcompletionfunctioncalloption) | Deprecated in favor of `tool_choice`.<br><br>Controls which (if any) function is called by the model.<br>`none` means the model won't call a function and instead generates a message.<br>`auto` means the model can pick between generating a message or calling a function.<br>Specifying a particular function via `{"name": "my_function"}` forces the model to call that function.<br><br>`none` is the default when no functions are present. `auto` is the default if functions are present.<br> | No |  |
 | functions | array | Deprecated in favor of `tools`.<br><br>A list of functions the model may generate JSON inputs for.<br> | No |  |
 | user_security_context | [userSecurityContext](#usersecuritycontext) | User security context contains several parameters that describe the AI application itself, and the end user that interacts with the AI application. These fields assist your security operations teams to investigate and mitigate security incidents by providing a comprehensive approach to protecting your AI applications. [Learn more](https://aka.ms/TP4AI/Documentation/EndUserContext) about protecting AI applications using Microsoft Defender for Cloud. | No |  | and detect abuse.<br> | No |  |
-| modalities | [ChatCompletionModalities](#chatcompletionmodalities) | Output types that you would like the model to generate for this request.<br>Most models are capable of generating text, which is the default:<br><br>`["text"]`<br><br>The `gpt-4o-audio-preview` model can also be used to [generate audio](/docs/guides/audio). To<br>request that this model generate both text and audio responses, you can<br>use:<br><br>`["text", "audio"]`<br> | No |  |
-| prediction | [PredictionContent](#predictioncontent) | Configuration for a [Predicted Output](/docs/guides/predicted-outputs), which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content. | No |  |
-| audio | object | Parameters for audio output. Required when audio output is requested with<br>`modalities: ["audio"]`. [Learn more](/docs/guides/audio).<br> | No |  |
+| modalities | [ChatCompletionModalities](#chatcompletionmodalities) | Output types that you would like the model to generate for this request.<br>Most models are capable of generating text, which is the default:<br><br>`["text"]`<br><br>The `gpt-4o-audio-preview` model can also be used to [generate audio](/azure/ai-services/openai/realtime-audio-quickstart). To<br>request that this model generate both text and audio responses, you can<br>use:<br><br>`["text", "audio"]`<br> | No |  |
+| prediction | [PredictionContent](#predictioncontent) | Configuration for a [Predicted Output](/azure/ai-services/openai/how-to/predicted-outputs), which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content. | No |  |
+| audio | object | Parameters for audio output. Required when audio output is requested with<br>`modalities: ["audio"]`. [Learn more](/azure/ai-services/openai/realtime-audio-quickstart).<br> | No |  |
 
 ### Properties for audio