Chat

ChatCompletions

List available chat completion models

client.chat.completions.models(?, ?): CompletionModelsResponse { items, object }

GET/v5/chat/completions/models

Generate OpenAI chat completion from messages

client.chat.completions.create(, ?): CompletionCreateResponse | Stream<ChatCompletionChunk { id, choices, created, 5 more } >

POST/v5/chat/completions

ModelsExpand Collapse

ChatCompletion { id, choices, created, 5 more }

id: string

choices: Array<Choice>

finish_reason: "stop" | "length" | "tool_calls" | 2 more

One of the following:

"stop"

"length"

"tool_calls"

"content_filter"

"function_call"

index: number

message: Message { role, annotations, audio, 4 more }

A chat completion message generated by the model.

role: "assistant"

annotations?: Array<Annotation>

type: "url_citation"

url_citation: URLCitation { end_index, start_index, title, url }

A URL citation when using web search.

end_index: number

start_index: number

title: string

url: string

audio?: Audio { 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.

id: string

data: string

expires_at: number

transcript: string

content?: string

function_call?: FunctionCall { arguments, name }

Deprecated and replaced by tool_calls.

The name and arguments of a function that should be called, as generated by the model.

arguments: string

refusal?: string

tool_calls?: Array<ChatCompletionMessageFunctionToolCall { id, function, type } | ChatCompletionMessageCustomToolCall { id, custom, type } >

One of the following:

ChatCompletionMessageFunctionToolCall { id, function, type }

A call to a function tool created by the model.

id: string

function: Function { arguments, name }

The function that the model called.

arguments: string

type: "function"

ChatCompletionMessageCustomToolCall { id, custom, type }

A call to a custom tool created by the model.

id: string

custom: Custom { input, name }

The custom tool that the model called.

input: string

type: "custom"

logprobs?: ChoiceLogprobs { content, refusal }

Log probability information for the choice.

content?: Array<ChatCompletionTokenLogprob { token, logprob, top_logprobs, bytes } >

token: string

logprob: number

top_logprobs: Array<TopLogprob>

token: string

logprob: number

bytes?: Array<number>

refusal?: Array<ChatCompletionTokenLogprob { token, logprob, top_logprobs, bytes } >

token: string

logprob: number

top_logprobs: Array<TopLogprob>

token: string

logprob: number

bytes?: Array<number>

created: number

model: string

object?: "chat.completion"

service_tier?: "auto" | "default" | "flex" | 2 more

One of the following:

"auto"

"default"

"flex"

"scale"

"priority"

system_fingerprint?: string

usage?: CompletionUsage { completion_tokens, prompt_tokens, total_tokens, 2 more }

Usage statistics for the completion request.

completion_tokens: number

prompt_tokens: number

total_tokens: number

completion_tokens_details?: CompletionTokensDetails { accepted_prediction_tokens, audio_tokens, reasoning_tokens, rejected_prediction_tokens }

Breakdown of tokens used in a completion.

accepted_prediction_tokens?: number

audio_tokens?: number

reasoning_tokens?: number

rejected_prediction_tokens?: number

prompt_tokens_details?: PromptTokensDetails { audio_tokens, cached_tokens }

Breakdown of tokens used in the prompt.

audio_tokens?: number

cached_tokens?: number

ChatCompletionChunk { id, choices, created, 5 more }

id: string

choices: Array<Choice>

delta: Delta { content, function_call, refusal, 2 more }

A chat completion delta generated by streamed model responses.

content?: string

function_call?: FunctionCall { arguments, name }

Deprecated and replaced by tool_calls.

The name and arguments of a function that should be called, as generated by the model.

arguments?: string

name?: string

refusal?: string

role?: "developer" | "system" | "user" | 2 more

One of the following:

"developer"

"system"

"user"

"assistant"

"tool"

tool_calls?: Array<ToolCall>

index: number

id?: string

function?: Function { arguments, name }

arguments?: string

name?: string

type?: "function"

index: number

finish_reason?: "stop" | "length" | "tool_calls" | 2 more

One of the following:

"stop"

"length"

"tool_calls"

"content_filter"

"function_call"

logprobs?: ChoiceLogprobs { content, refusal }

Log probability information for the choice.

content?: Array<ChatCompletionTokenLogprob { token, logprob, top_logprobs, bytes } >

token: string

logprob: number

top_logprobs: Array<TopLogprob>

token: string

logprob: number

bytes?: Array<number>

refusal?: Array<ChatCompletionTokenLogprob { token, logprob, top_logprobs, bytes } >

token: string

logprob: number

top_logprobs: Array<TopLogprob>

token: string

logprob: number

bytes?: Array<number>

created: number

model: string

object?: "chat.completion.chunk"

service_tier?: "auto" | "default" | "flex" | 2 more

One of the following:

"auto"

"default"

"flex"

"scale"

"priority"

system_fingerprint?: string

usage?: CompletionUsage { completion_tokens, prompt_tokens, total_tokens, 2 more }

Usage statistics for the completion request.

completion_tokens: number

prompt_tokens: number

total_tokens: number

completion_tokens_details?: CompletionTokensDetails { accepted_prediction_tokens, audio_tokens, reasoning_tokens, rejected_prediction_tokens }

Breakdown of tokens used in a completion.

accepted_prediction_tokens?: number

audio_tokens?: number

reasoning_tokens?: number

rejected_prediction_tokens?: number

prompt_tokens_details?: PromptTokensDetails { audio_tokens, cached_tokens }

Breakdown of tokens used in the prompt.

audio_tokens?: number

cached_tokens?: number

ChatCompletionTokenLogprob { token, logprob, top_logprobs, bytes }

token: string

logprob: number

top_logprobs: Array<TopLogprob>

token: string

logprob: number

bytes?: Array<number>

ChoiceLogprobs { content, refusal }

Log probability information for the choice.

content?: Array<ChatCompletionTokenLogprob { token, logprob, top_logprobs, bytes } >

token: string

logprob: number

top_logprobs: Array<TopLogprob>

token: string

logprob: number

bytes?: Array<number>

refusal?: Array<ChatCompletionTokenLogprob { token, logprob, top_logprobs, bytes } >

token: string

logprob: number

top_logprobs: Array<TopLogprob>

token: string

logprob: number

bytes?: Array<number>

InferenceModelVendor = "openai" | "cohere" | "vertex_ai" | 9 more

One of the following:

"openai"

"cohere"

"vertex_ai"

"anthropic"

"azure"

"gemini"

"launch"

"llmengine"

"model_zoo"

"bedrock"

"xai"

"fireworks_ai"

ModelDefinition { model_name, model_type, model_vendor, model_availability }

model_name: string

model name, for example gpt-4o

model_type: InferenceModelType

model type, for example chat_completion

One of the following:

"generic"

"completion"

"chat_completion"

model_vendor: InferenceModelVendor

model vendor, for example openai

One of the following:

"openai"

"cohere"

"vertex_ai"

"anthropic"

"azure"

"gemini"

"launch"

"llmengine"

"model_zoo"

"bedrock"

"xai"

"fireworks_ai"

model_availability?: InferenceModelAvailability

model availability indicating availability status, for example available

One of the following:

"unknown"

"available"

"unavailable"

SortOrder = "asc" | "desc"

One of the following:

"asc"

"desc"

CompletionModelsResponse { items, object }

items: Array<ModelDefinition { model_name, model_type, model_vendor, model_availability } >

model_name: string

model name, for example gpt-4o

model_type: InferenceModelType

model type, for example chat_completion

One of the following:

"generic"

"completion"

"chat_completion"

model_vendor: InferenceModelVendor

model vendor, for example openai

One of the following:

"openai"

"cohere"

"vertex_ai"

"anthropic"

"azure"

"gemini"

"launch"

"llmengine"

"model_zoo"

"bedrock"

"xai"

"fireworks_ai"

model_availability?: InferenceModelAvailability

model availability indicating availability status, for example available

One of the following:

"unknown"

"available"

"unavailable"

object?: "list"

CompletionCreateResponse = ChatCompletion { id, choices, created, 5 more } | ChatCompletionChunk { id, choices, created, 5 more }

One of the following:

ChatCompletion { id, choices, created, 5 more }

id: string

choices: Array<Choice>

finish_reason: "stop" | "length" | "tool_calls" | 2 more

One of the following:

"stop"

"length"

"tool_calls"

"content_filter"

"function_call"

index: number

message: Message { role, annotations, audio, 4 more }

A chat completion message generated by the model.

role: "assistant"

annotations?: Array<Annotation>

type: "url_citation"

url_citation: URLCitation { end_index, start_index, title, url }

A URL citation when using web search.

end_index: number

start_index: number

title: string

url: string

audio?: Audio { 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.

id: string

data: string

expires_at: number

transcript: string

content?: string

function_call?: FunctionCall { arguments, name }

Deprecated and replaced by tool_calls.

The name and arguments of a function that should be called, as generated by the model.

arguments: string

refusal?: string

tool_calls?: Array<ChatCompletionMessageFunctionToolCall { id, function, type } | ChatCompletionMessageCustomToolCall { id, custom, type } >

One of the following:

ChatCompletionMessageFunctionToolCall { id, function, type }

A call to a function tool created by the model.

id: string

function: Function { arguments, name }

The function that the model called.

arguments: string

type: "function"

ChatCompletionMessageCustomToolCall { id, custom, type }

A call to a custom tool created by the model.

id: string

custom: Custom { input, name }

The custom tool that the model called.

input: string

type: "custom"

logprobs?: ChoiceLogprobs { content, refusal }

Log probability information for the choice.

content?: Array<ChatCompletionTokenLogprob { token, logprob, top_logprobs, bytes } >

token: string

logprob: number

top_logprobs: Array<TopLogprob>

token: string

logprob: number

bytes?: Array<number>

refusal?: Array<ChatCompletionTokenLogprob { token, logprob, top_logprobs, bytes } >

token: string

logprob: number

top_logprobs: Array<TopLogprob>

token: string

logprob: number

bytes?: Array<number>

created: number

model: string

object?: "chat.completion"

service_tier?: "auto" | "default" | "flex" | 2 more

One of the following:

"auto"

"default"

"flex"

"scale"

"priority"

system_fingerprint?: string

usage?: CompletionUsage { completion_tokens, prompt_tokens, total_tokens, 2 more }

Usage statistics for the completion request.

completion_tokens: number

prompt_tokens: number

total_tokens: number

completion_tokens_details?: CompletionTokensDetails { accepted_prediction_tokens, audio_tokens, reasoning_tokens, rejected_prediction_tokens }

Breakdown of tokens used in a completion.

accepted_prediction_tokens?: number

audio_tokens?: number

reasoning_tokens?: number

rejected_prediction_tokens?: number

prompt_tokens_details?: PromptTokensDetails { audio_tokens, cached_tokens }

Breakdown of tokens used in the prompt.

audio_tokens?: number

cached_tokens?: number

ChatCompletionChunk { id, choices, created, 5 more }

id: string

choices: Array<Choice>

delta: Delta { content, function_call, refusal, 2 more }

A chat completion delta generated by streamed model responses.

content?: string

function_call?: FunctionCall { arguments, name }

Deprecated and replaced by tool_calls.

The name and arguments of a function that should be called, as generated by the model.

arguments?: string

name?: string

refusal?: string

role?: "developer" | "system" | "user" | 2 more

One of the following:

"developer"

"system"

"user"

"assistant"

"tool"

tool_calls?: Array<ToolCall>

index: number

id?: string

function?: Function { arguments, name }

arguments?: string

name?: string

type?: "function"

index: number

finish_reason?: "stop" | "length" | "tool_calls" | 2 more

One of the following:

"stop"

"length"

"tool_calls"

"content_filter"

"function_call"

logprobs?: ChoiceLogprobs { content, refusal }

Log probability information for the choice.

content?: Array<ChatCompletionTokenLogprob { token, logprob, top_logprobs, bytes } >

token: string

logprob: number

top_logprobs: Array<TopLogprob>

token: string

logprob: number

bytes?: Array<number>

refusal?: Array<ChatCompletionTokenLogprob { token, logprob, top_logprobs, bytes } >

token: string

logprob: number

top_logprobs: Array<TopLogprob>

token: string

logprob: number

bytes?: Array<number>

created: number

model: string

object?: "chat.completion.chunk"

service_tier?: "auto" | "default" | "flex" | 2 more

One of the following:

"auto"

"default"

"flex"

"scale"

"priority"

system_fingerprint?: string

usage?: CompletionUsage { completion_tokens, prompt_tokens, total_tokens, 2 more }

Usage statistics for the completion request.

completion_tokens: number

prompt_tokens: number

total_tokens: number

completion_tokens_details?: CompletionTokensDetails { accepted_prediction_tokens, audio_tokens, reasoning_tokens, rejected_prediction_tokens }

Breakdown of tokens used in a completion.

accepted_prediction_tokens?: number

audio_tokens?: number

reasoning_tokens?: number

rejected_prediction_tokens?: number

prompt_tokens_details?: PromptTokensDetails { audio_tokens, cached_tokens }

Breakdown of tokens used in the prompt.

audio_tokens?: number

cached_tokens?: number