ChatCompletionModalities
arrayOutput types that you would like the model to generate for this request.
Most models are capable of generating text, which is the default:
["text"]
The gpt-4o-audio-preview model can also be used to generate audio. To
request that this model generate both text and audio responses, you can
use:
["text", "audio"]
ChatCompletionNamedToolChoice
objectSpecifies a tool the model should use. Use to force the model to call a specific function.
The type of the tool. Currently, only function is supported.
Allowed values:function
Show Child Parameters
Assistant message
objectMessages sent by the model in response to user messages.
One OfThe contents of the assistant message. Required unless tool_calls or function_call is specified.
The contents of the assistant message.
The refusal message by the assistant.
The role of the messages author, in this case assistant.
Allowed values:assistant
An optional name for the participant. Provides the model information to differentiate between participants of the same role.
Data about a previous audio response from the model.
Learn more.
Show Child Parameters
The tool calls generated by the model, such as function calls.
Show Child Parameters
Deprecated and replaced by tool_calls. The name and arguments of a function that should be called, as generated by the model.
Show Child Parameters
ChatCompletionRequestAssistantMessageContentPart
One OfThe type of the content part.
Allowed values:text
The text content.
Developer message
objectDeveloper-provided instructions that the model should follow, regardless of
messages sent by the user. With o1 models and newer, developer messages
replace the previous system messages.
One OfThe contents of the developer message.
The contents of the developer message.
The role of the messages author, in this case developer.
Allowed values:developer
An optional name for the participant. Provides the model information to differentiate between participants of the same role.