Skip to content
For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.
Primary navigation

Suggested
Overview Models Agents Tools Audio & voice Production API reference

Chat

ChatCompletions

Given a list of messages comprising a conversation, the model will return a response.

Create chat completion
client.chat.completions.create(body, options?): ChatCompletion { id, choices, created, 7 more } | Stream<ChatCompletionChunk { id, choices, created, 7 more } >
POST
/chat/completions
Delete chat completion
client.chat.completions.delete(completionID, options?): ChatCompletionDeleted { id, deleted, object }
DELETE
/chat/completions/{completion_id}
List Chat Completions
client.chat.completions.list(query?, options?): CursorPage<ChatCompletion { id, choices, created, 7 more } >
GET
/chat/completions
Get chat completion
client.chat.completions.retrieve(completionID, options?): ChatCompletion { id, choices, created, 7 more }
GET
/chat/completions/{completion_id}
Update chat completion
client.chat.completions.update(completionID, body, options?): ChatCompletion { id, choices, created, 7 more }
POST
/chat/completions/{completion_id}
Models
ChatCompletionAllowedTools { mode, tools }

Constrains the tools available to the model to a pre-defined set.

ChatCompletion { id, choices, created, 7 more }

Represents a chat completion response returned by model, based on the provided input.

ChatCompletionAllowedToolChoice { allowed_tools, type }

Constrains the tools available to the model to a pre-defined set.

ChatCompletionAssistantMessageParam { role, audio, content, 4 more }

Messages sent by the model in response to user messages.

ChatCompletionAudio { id, data, expires_at, transcript }

If the audio output modality is requested, this object contains data about the audio response from the model. Learn more.

ChatCompletionAudioParam { format, voice }

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.

ChatCompletionChunk { id, choices, created, 7 more }

Represents a streamed chunk of a chat completion response returned by the model, based on the provided input. Learn more.

ChatCompletionContentPart = ChatCompletionContentPartText { text, type, prompt_cache_breakpoint } | ChatCompletionContentPartImage { image_url, type, prompt_cache_breakpoint } | ChatCompletionContentPartInputAudio { input_audio, type, prompt_cache_breakpoint } | File { file, type, prompt_cache_breakpoint }

Learn about text inputs.

ChatCompletionContentPartImage { image_url, type, prompt_cache_breakpoint }

Learn about image inputs.

ChatCompletionContentPartInputAudio { input_audio, type, prompt_cache_breakpoint }

Learn about audio inputs.

ChatCompletionContentPartRefusal { refusal, type }
ChatCompletionContentPartText { text, type, prompt_cache_breakpoint }

Learn about text inputs.

ChatCompletionCustomTool { custom, type }

A custom tool that processes input using a specified format.

ChatCompletionDeleted { id, deleted, object }
ChatCompletionDeveloperMessageParam { content, role, name }

Developer-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.

ChatCompletionFunctionCallOption { name }

Specifying a particular function via {"name": "my_function"} forces the model to call that function.

ChatCompletionFunctionMessageParam { content, name, role }
ChatCompletionFunctionTool { function, type }

A function tool that can be used to generate a response.

ChatCompletionMessage { content, refusal, role, 4 more }

A chat completion message generated by the model.

ChatCompletionMessageCustomToolCall { id, custom, type }

A call to a custom tool created by the model.

ChatCompletionMessageFunctionToolCall { id, function, type }

A call to a function tool created by the model.

ChatCompletionMessageParam = ChatCompletionDeveloperMessageParam { content, role, name } | ChatCompletionSystemMessageParam { content, role, name } | ChatCompletionUserMessageParam { content, role, name } | 3 more

Developer-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.

ChatCompletionMessageToolCall = ChatCompletionMessageFunctionToolCall { id, function, type } | ChatCompletionMessageCustomToolCall { id, custom, type }

A call to a function tool created by the model.

ChatCompletionModality = "text" | "audio"
ChatCompletionNamedToolChoice { function, type }

Specifies a tool the model should use. Use to force the model to call a specific function.

ChatCompletionNamedToolChoiceCustom { custom, type }

Specifies a tool the model should use. Use to force the model to call a specific custom tool.

ChatCompletionPredictionContent { content, type }

Static predicted output content, such as the content of a text file that is being regenerated.

ChatCompletionRole = "developer" | "system" | "user" | 3 more

The role of the author of a message

ChatCompletionStoreMessage extends ChatCompletionMessage { content, refusal, role, 4 more } { id, content_parts }

A chat completion message generated by the model.

ChatCompletionStreamOptions { include_obfuscation, include_usage }

Options for streaming response. Only set this when you set stream: true.

ChatCompletionSystemMessageParam { content, role, name }

Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, use developer messages for this purpose instead.

ChatCompletionTokenLogprob { token, bytes, logprob, top_logprobs }
ChatCompletionTool = ChatCompletionFunctionTool { function, type } | ChatCompletionCustomTool { custom, type }

A function tool that can be used to generate a response.

ChatCompletionToolChoiceOption = "none" | "auto" | "required" | ChatCompletionAllowedToolChoice { allowed_tools, type } | ChatCompletionNamedToolChoice { function, type } | ChatCompletionNamedToolChoiceCustom { custom, type }

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

none is the default when no tools are present. auto is the default if tools are present.

ChatCompletionToolMessageParam { content, role, tool_call_id }
ChatCompletionUserMessageParam { content, role, name }

Messages sent by an end user, containing prompts or additional context information.

ChatCompletionsMessages

Given a list of messages comprising a conversation, the model will return a response.

Get chat messages
client.chat.completions.messages.list(completionID, query?, options?): CursorPage<ChatCompletionStoreMessage { id, content_parts } >
GET
/chat/completions/{completion_id}/messages