Readonly_The chat completion response.
ReadonlyrawParses the response and returns the choice by index.
The index of the choice to find.
An LLMChoice object associated with the index.
Optionalcontent_filter_results?: AzureOpenAiContentFilterChoiceResultsThe reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence,
length if the maximum number of tokens specified in the request was reached,
content_filter if content was omitted due to a flag from our content filters,
tool_calls if the model called a tool, or function_call (deprecated) if the model called a function.
The index of the choice in the list of choices.
Log probability information for the choice.
Gets the assistant message from the response.
OptionalchoiceIndex: numberThe index of the choice to use (default is 0).
The assistant message.
Parses the Azure OpenAI response and returns the content.
OptionalchoiceIndex: numberThe index of the choice to parse.
The message content.
Reason for stopping the completion.
OptionalchoiceIndex: numberThe index of the choice to parse.
The finish reason.
Parses the Azure OpenAI response and returns the refusal message generated by the model.
OptionalchoiceIndex: numberThe index of the choice to parse.
The refusal string.
Usage of tokens in the response.
Token usage.
Parses the Azure OpenAI response and returns the tool calls generated by the model.
OptionalchoiceIndex: numberThe index of the choice to parse.
The message tool calls.
Copyright Ⓒ 2026 SAP SE or an SAP affiliate company. All rights reserved.
Azure OpenAI chat completion response.