Skip to content
API Reference
Chat

Completions

Create chat completion
chat.completions.create(**kwargs) -> ChatCompletion { id, choices, created, 5 more }
POST/chat/completions
List Chat Completions
chat.completions.list(**kwargs) -> CursorPage<ChatCompletion { id, choices, created, 5 more } >
GET/chat/completions
Get chat completion
chat.completions.retrieve(completion_id) -> ChatCompletion { id, choices, created, 5 more }
GET/chat/completions/{completion_id}
Update chat completion
chat.completions.update(completion_id, **kwargs) -> ChatCompletion { id, choices, created, 5 more }
POST/chat/completions/{completion_id}
Delete chat completion
chat.completions.delete(completion_id) -> ChatCompletionDeleted { id, deleted, object }
DELETE/chat/completions/{completion_id}
ModelsExpand Collapse
class ChatCompletion { id, choices, created, 5 more }

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

id: String

A unique identifier for the chat completion.

choices: Array[{ finish_reason, index, logprobs, message}]

A list of chat completion choices. Can be more than one if n is greater than 1.

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

The 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.

Accepts one of the following:
:stop
:length
:tool_calls
:content_filter
:function_call
index: Integer

The index of the choice in the list of choices.

logprobs: { content, refusal}

Log probability information for the choice.

content: Array[ChatCompletionTokenLogprob { token, bytes, logprob, top_logprobs } ]

A list of message content tokens with log probability information.

token: String

The token.

bytes: Array[Integer]

A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.

logprob: Float

The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.

top_logprobs: Array[{ token, bytes, logprob}]

List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.

token: String

The token.

bytes: Array[Integer]

A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.

logprob: Float

The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.

refusal: Array[ChatCompletionTokenLogprob { token, bytes, logprob, top_logprobs } ]

A list of message refusal tokens with log probability information.

token: String

The token.

bytes: Array[Integer]

A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.

logprob: Float

The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.

top_logprobs: Array[{ token, bytes, logprob}]

List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.

token: String

The token.

bytes: Array[Integer]

A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.

logprob: Float

The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.

message: ChatCompletionMessage { content, refusal, role, 4 more }

A chat completion message generated by the model.

created: Integer

The Unix timestamp (in seconds) of when the chat completion was created.

model: String

The model used for the chat completion.

object: :"chat.completion"

The object type, which is always chat.completion.

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

Specifies the processing type used for serving the request.

  • If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
  • If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
  • If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
  • When not set, the default behavior is 'auto'.

When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.

Accepts one of the following:
:auto
:default
:flex
:scale
:priority
Deprecatedsystem_fingerprint: String

This fingerprint represents the backend configuration that the model runs with.

Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.

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

Usage statistics for the completion request.

class ChatCompletionAllowedToolChoice { allowed_tools, type }

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

allowed_tools: ChatCompletionAllowedTools { mode, tools }

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

type: :allowed_tools

Allowed tool configuration type. Always allowed_tools.

class ChatCompletionAssistantMessageParam { role, audio, content, 4 more }

Messages sent by the model in response to user messages.

role: :assistant

The role of the messages author, in this case assistant.

audio: { id}

Data about a previous audio response from the model. Learn more.

id: String

Unique identifier for a previous audio response from the model.

content: String | Array[ChatCompletionContentPartText { text, type } | ChatCompletionContentPartRefusal { refusal, type } ]

The contents of the assistant message. Required unless tool_calls or function_call is specified.

Accepts one of the following:
String

The contents of the assistant message.

Array[ChatCompletionContentPartText { text, type } | ChatCompletionContentPartRefusal { refusal, type } ]

An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal.

Accepts one of the following:
class ChatCompletionContentPartText { text, type }

Learn about text inputs.

text: String

The text content.

type: :text

The type of the content part.

class ChatCompletionContentPartRefusal { refusal, type }
refusal: String

The refusal message generated by the model.

type: :refusal

The type of the content part.

Deprecatedfunction_call: { 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

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name: String

The name of the function to call.

name: String

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

refusal: String

The refusal message by the assistant.

tool_calls: Array[ChatCompletionMessageToolCall]

The tool calls generated by the model, such as function calls.

Accepts one of the following:
class ChatCompletionMessageFunctionToolCall { id, function, type }

A call to a function tool created by the model.

id: String

The ID of the tool call.

function: { arguments, name}

The function that the model called.

arguments: String

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name: String

The name of the function to call.

type: :function

The type of the tool. Currently, only function is supported.

class ChatCompletionMessageCustomToolCall { id, custom, type }

A call to a custom tool created by the model.

id: String

The ID of the tool call.

custom: { input, name}

The custom tool that the model called.

input: String

The input for the custom tool call generated by the model.

name: String

The name of the custom tool to call.

type: :custom

The type of the tool. Always custom.

class 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.

id: String

Unique identifier for this audio response.

data: String

Base64 encoded audio bytes generated by the model, in the format specified in the request.

expires_at: Integer

The Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations.

transcript: String

Transcript of the audio generated by the model.

class ChatCompletionAudioParam { format_, voice }

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

format_: :wav | :aac | :mp3 | 3 more

Specifies the output audio format. Must be one of wav, mp3, flac, opus, or pcm16.

Accepts one of the following:
:wav
:aac
:mp3
:flac
:opus
:pcm16
voice: String | :alloy | :ash | :ballad | 7 more

The voice the model uses to respond. Supported built-in voices are alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, shimmer, marin, and cedar.

Accepts one of the following:
String
:alloy | :ash | :ballad | 7 more

The voice the model uses to respond. Supported built-in voices are alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, shimmer, marin, and cedar.

Accepts one of the following:
:alloy
:ash
:ballad
:coral
:echo
:sage
:shimmer
:verse
:marin
:cedar
class ChatCompletionChunk { id, choices, created, 5 more }

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

id: String

A unique identifier for the chat completion. Each chunk has the same ID.

choices: Array[{ delta, finish_reason, index, logprobs}]

A list of chat completion choices. Can contain more than one elements if n is greater than 1. Can also be empty for the last chunk if you set stream_options: {"include_usage": true}.

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

A chat completion delta generated by streamed model responses.

content: String

The contents of the chunk message.

Deprecatedfunction_call: { 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

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name: String

The name of the function to call.

refusal: String

The refusal message generated by the model.

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

The role of the author of this message.

Accepts one of the following:
:developer
:system
:user
:assistant
:tool
tool_calls: Array[{ index, id, function, type}]
index: Integer
id: String

The ID of the tool call.

function: { arguments, name}
arguments: String

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name: String

The name of the function to call.

type: :function

The type of the tool. Currently, only function is supported.

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

The 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.

Accepts one of the following:
:stop
:length
:tool_calls
:content_filter
:function_call
index: Integer

The index of the choice in the list of choices.

logprobs: { content, refusal}

Log probability information for the choice.

content: Array[ChatCompletionTokenLogprob { token, bytes, logprob, top_logprobs } ]

A list of message content tokens with log probability information.

token: String

The token.

bytes: Array[Integer]

A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.

logprob: Float

The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.

top_logprobs: Array[{ token, bytes, logprob}]

List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.

token: String

The token.

bytes: Array[Integer]

A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.

logprob: Float

The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.

refusal: Array[ChatCompletionTokenLogprob { token, bytes, logprob, top_logprobs } ]

A list of message refusal tokens with log probability information.

token: String

The token.

bytes: Array[Integer]

A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.

logprob: Float

The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.

top_logprobs: Array[{ token, bytes, logprob}]

List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.

token: String

The token.

bytes: Array[Integer]

A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.

logprob: Float

The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.

created: Integer

The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp.

model: String

The model to generate the completion.

object: :"chat.completion.chunk"

The object type, which is always chat.completion.chunk.

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

Specifies the processing type used for serving the request.

  • If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
  • If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
  • If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
  • When not set, the default behavior is 'auto'.

When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.

Accepts one of the following:
:auto
:default
:flex
:scale
:priority
Deprecatedsystem_fingerprint: String

This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.

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

An optional field that will only be present when you set stream_options: {"include_usage": true} in your request. When present, it contains a null value except for the last chunk which contains the token usage statistics for the entire request.

NOTE: If the stream is interrupted or cancelled, you may not receive the final usage chunk which contains the total token usage for the request.

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

Learn about text inputs.

Accepts one of the following:
class ChatCompletionContentPartText { text, type }

Learn about text inputs.

text: String

The text content.

type: :text

The type of the content part.

class ChatCompletionContentPartImage { image_url, type }

Learn about image inputs.

image_url: { url, detail}
url: String

Either a URL of the image or the base64 encoded image data.

formaturi
detail: :auto | :low | :high

Specifies the detail level of the image. Learn more in the Vision guide.

Accepts one of the following:
:auto
:low
:high
type: :image_url

The type of the content part.

class ChatCompletionContentPartInputAudio { input_audio, type }

Learn about audio inputs.

input_audio: { data, format_}
data: String

Base64 encoded audio data.

format_: :wav | :mp3

The format of the encoded audio data. Currently supports "wav" and "mp3".

Accepts one of the following:
:wav
:mp3
type: :input_audio

The type of the content part. Always input_audio.

class File { file, type }

Learn about file inputs for text generation.

file: { file_data, file_id, filename}
file_data: String

The base64 encoded file data, used when passing the file to the model as a string.

file_id: String

The ID of an uploaded file to use as input.

filename: String

The name of the file, used when passing the file to the model as a string.

type: :file

The type of the content part. Always file.

class ChatCompletionContentPartImage { image_url, type }

Learn about image inputs.

image_url: { url, detail}
url: String

Either a URL of the image or the base64 encoded image data.

formaturi
detail: :auto | :low | :high

Specifies the detail level of the image. Learn more in the Vision guide.

Accepts one of the following:
:auto
:low
:high
type: :image_url

The type of the content part.

class ChatCompletionContentPartInputAudio { input_audio, type }

Learn about audio inputs.

input_audio: { data, format_}
data: String

Base64 encoded audio data.

format_: :wav | :mp3

The format of the encoded audio data. Currently supports "wav" and "mp3".

Accepts one of the following:
:wav
:mp3
type: :input_audio

The type of the content part. Always input_audio.

class ChatCompletionContentPartRefusal { refusal, type }
refusal: String

The refusal message generated by the model.

type: :refusal

The type of the content part.

class ChatCompletionContentPartText { text, type }

Learn about text inputs.

text: String

The text content.

type: :text

The type of the content part.

class ChatCompletionCustomTool { custom, type }

A custom tool that processes input using a specified format.

custom: { name, description, format_}

Properties of the custom tool.

name: String

The name of the custom tool, used to identify it in tool calls.

description: String

Optional description of the custom tool, used to provide more context.

format_: { type} | { grammar, type}

The input format for the custom tool. Default is unconstrained text.

Accepts one of the following:
class Text { type }

Unconstrained free-form text.

type: :text

Unconstrained text format. Always text.

class Grammar { grammar, type }

A grammar defined by the user.

grammar: { definition, syntax}

Your chosen grammar.

definition: String

The grammar definition.

syntax: :lark | :regex

The syntax of the grammar definition. One of lark or regex.

Accepts one of the following:
:lark
:regex
type: :grammar

Grammar format. Always grammar.

type: :custom

The type of the custom tool. Always custom.

class ChatCompletionDeleted { id, deleted, object }
id: String

The ID of the chat completion that was deleted.

deleted: bool

Whether the chat completion was deleted.

object: :"chat.completion.deleted"

The type of object being deleted.

class 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.

content: String | Array[ChatCompletionContentPartText { text, type } ]

The contents of the developer message.

Accepts one of the following:
String

The contents of the developer message.

Array[ChatCompletionContentPartText { text, type } ]

An array of content parts with a defined type. For developer messages, only type text is supported.

text: String

The text content.

type: :text

The type of the content part.

role: :developer

The role of the messages author, in this case developer.

name: String

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

class ChatCompletionFunctionCallOption { name }

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

name: String

The name of the function to call.

class ChatCompletionFunctionMessageParam { content, name, role }
content: String

The contents of the function message.

name: String

The name of the function to call.

role: :function

The role of the messages author, in this case function.

class ChatCompletionFunctionTool { function, type }

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

function: FunctionDefinition { name, description, parameters, strict }
type: :function

The type of the tool. Currently, only function is supported.

class ChatCompletionMessage { content, refusal, role, 4 more }

A chat completion message generated by the model.

content: String

The contents of the message.

refusal: String

The refusal message generated by the model.

role: :assistant

The role of the author of this message.

annotations: Array[{ type, url_citation}]

Annotations for the message, when applicable, as when using the web search tool.

type: :url_citation

The type of the URL citation. Always url_citation.

url_citation: { end_index, start_index, title, url}

A URL citation when using web search.

end_index: Integer

The index of the last character of the URL citation in the message.

start_index: Integer

The index of the first character of the URL citation in the message.

title: String

The title of the web resource.

url: String

The URL of the web resource.

audio: 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.

Deprecatedfunction_call: { 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

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name: String

The name of the function to call.

tool_calls: Array[ChatCompletionMessageToolCall]

The tool calls generated by the model, such as function calls.

Accepts one of the following:
class ChatCompletionMessageFunctionToolCall { id, function, type }

A call to a function tool created by the model.

id: String

The ID of the tool call.

function: { arguments, name}

The function that the model called.

arguments: String

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name: String

The name of the function to call.

type: :function

The type of the tool. Currently, only function is supported.

class ChatCompletionMessageCustomToolCall { id, custom, type }

A call to a custom tool created by the model.

id: String

The ID of the tool call.

custom: { input, name}

The custom tool that the model called.

input: String

The input for the custom tool call generated by the model.

name: String

The name of the custom tool to call.

type: :custom

The type of the tool. Always custom.

class ChatCompletionMessageCustomToolCall { id, custom, type }

A call to a custom tool created by the model.

id: String

The ID of the tool call.

custom: { input, name}

The custom tool that the model called.

input: String

The input for the custom tool call generated by the model.

name: String

The name of the custom tool to call.

type: :custom

The type of the tool. Always custom.

class ChatCompletionMessageFunctionToolCall { id, function, type }

A call to a function tool created by the model.

id: String

The ID of the tool call.

function: { arguments, name}

The function that the model called.

arguments: String

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name: String

The name of the function to call.

type: :function

The type of the tool. Currently, only function is supported.

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.

Accepts one of the following:
class 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.

content: String | Array[ChatCompletionContentPartText { text, type } ]

The contents of the developer message.

Accepts one of the following:
String

The contents of the developer message.

Array[ChatCompletionContentPartText { text, type } ]

An array of content parts with a defined type. For developer messages, only type text is supported.

text: String

The text content.

type: :text

The type of the content part.

role: :developer

The role of the messages author, in this case developer.

name: String

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

class 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.

content: String | Array[ChatCompletionContentPartText { text, type } ]

The contents of the system message.

Accepts one of the following:
String

The contents of the system message.

Array[ChatCompletionContentPartText { text, type } ]

An array of content parts with a defined type. For system messages, only type text is supported.

text: String

The text content.

type: :text

The type of the content part.

role: :system

The role of the messages author, in this case system.

name: String

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

class ChatCompletionUserMessageParam { content, role, name }

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

content: String | Array[ChatCompletionContentPart]

The contents of the user message.

Accepts one of the following:
String

The text contents of the message.

Array[ChatCompletionContentPart]

An array of content parts with a defined type. Supported options differ based on the model being used to generate the response. Can contain text, image, or audio inputs.

Accepts one of the following:
class ChatCompletionContentPartText { text, type }

Learn about text inputs.

text: String

The text content.

type: :text

The type of the content part.

class ChatCompletionContentPartImage { image_url, type }

Learn about image inputs.

image_url: { url, detail}
url: String

Either a URL of the image or the base64 encoded image data.

formaturi
detail: :auto | :low | :high

Specifies the detail level of the image. Learn more in the Vision guide.

Accepts one of the following:
:auto
:low
:high
type: :image_url

The type of the content part.

class ChatCompletionContentPartInputAudio { input_audio, type }

Learn about audio inputs.

input_audio: { data, format_}
data: String

Base64 encoded audio data.

format_: :wav | :mp3

The format of the encoded audio data. Currently supports "wav" and "mp3".

Accepts one of the following:
:wav
:mp3
type: :input_audio

The type of the content part. Always input_audio.

class File { file, type }

Learn about file inputs for text generation.

file: { file_data, file_id, filename}
file_data: String

The base64 encoded file data, used when passing the file to the model as a string.

file_id: String

The ID of an uploaded file to use as input.

filename: String

The name of the file, used when passing the file to the model as a string.

type: :file

The type of the content part. Always file.

role: :user

The role of the messages author, in this case user.

name: String

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

class ChatCompletionAssistantMessageParam { role, audio, content, 4 more }

Messages sent by the model in response to user messages.

role: :assistant

The role of the messages author, in this case assistant.

audio: { id}

Data about a previous audio response from the model. Learn more.

id: String

Unique identifier for a previous audio response from the model.

content: String | Array[ChatCompletionContentPartText { text, type } | ChatCompletionContentPartRefusal { refusal, type } ]

The contents of the assistant message. Required unless tool_calls or function_call is specified.

Accepts one of the following:
String

The contents of the assistant message.

Array[ChatCompletionContentPartText { text, type } | ChatCompletionContentPartRefusal { refusal, type } ]

An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal.

Accepts one of the following:
class ChatCompletionContentPartText { text, type }

Learn about text inputs.

text: String

The text content.

type: :text

The type of the content part.

class ChatCompletionContentPartRefusal { refusal, type }
refusal: String

The refusal message generated by the model.

type: :refusal

The type of the content part.

Deprecatedfunction_call: { 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

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name: String

The name of the function to call.

name: String

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

refusal: String

The refusal message by the assistant.

tool_calls: Array[ChatCompletionMessageToolCall]

The tool calls generated by the model, such as function calls.

Accepts one of the following:
class ChatCompletionMessageFunctionToolCall { id, function, type }

A call to a function tool created by the model.

id: String

The ID of the tool call.

function: { arguments, name}

The function that the model called.

arguments: String

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name: String

The name of the function to call.

type: :function

The type of the tool. Currently, only function is supported.

class ChatCompletionMessageCustomToolCall { id, custom, type }

A call to a custom tool created by the model.

id: String

The ID of the tool call.

custom: { input, name}

The custom tool that the model called.

input: String

The input for the custom tool call generated by the model.

name: String

The name of the custom tool to call.

type: :custom

The type of the tool. Always custom.

class ChatCompletionToolMessageParam { content, role, tool_call_id }
content: String | Array[ChatCompletionContentPartText { text, type } ]

The contents of the tool message.

Accepts one of the following:
String

The contents of the tool message.

Array[ChatCompletionContentPartText { text, type } ]

An array of content parts with a defined type. For tool messages, only type text is supported.

text: String

The text content.

type: :text

The type of the content part.

role: :tool

The role of the messages author, in this case tool.

tool_call_id: String

Tool call that this message is responding to.

class ChatCompletionFunctionMessageParam { content, name, role }
content: String

The contents of the function message.

name: String

The name of the function to call.

role: :function

The role of the messages author, in this case function.

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

A call to a function tool created by the model.

Accepts one of the following:
class ChatCompletionMessageFunctionToolCall { id, function, type }

A call to a function tool created by the model.

id: String

The ID of the tool call.

function: { arguments, name}

The function that the model called.

arguments: String

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name: String

The name of the function to call.

type: :function

The type of the tool. Currently, only function is supported.

class ChatCompletionMessageCustomToolCall { id, custom, type }

A call to a custom tool created by the model.

id: String

The ID of the tool call.

custom: { input, name}

The custom tool that the model called.

input: String

The input for the custom tool call generated by the model.

name: String

The name of the custom tool to call.

type: :custom

The type of the tool. Always custom.

ChatCompletionModality = :text | :audio
Accepts one of the following:
:text
:audio
class ChatCompletionNamedToolChoice { function, type }

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

function: { name}
name: String

The name of the function to call.

type: :function

For function calling, the type is always function.

class ChatCompletionNamedToolChoiceCustom { custom, type }

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

custom: { name}
name: String

The name of the custom tool to call.

type: :custom

For custom tool calling, the type is always custom.

class ChatCompletionPredictionContent { content, type }

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

content: String | Array[ChatCompletionContentPartText { text, type } ]

The content that should be matched when generating a model response. If generated tokens would match this content, the entire model response can be returned much more quickly.

Accepts one of the following:
String

The content used for a Predicted Output. This is often the text of a file you are regenerating with minor changes.

Array[ChatCompletionContentPartText { text, type } ]

An array of content parts with a defined type. Supported options differ based on the model being used to generate the response. Can contain text inputs.

text: String

The text content.

type: :text

The type of the content part.

type: :content

The type of the predicted content you want to provide. This type is currently always content.

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

The role of the author of a message

Accepts one of the following:
:developer
:system
:user
:assistant
:tool
:function
class ChatCompletionStoreMessage { id, content_parts }

A chat completion message generated by the model.

id: String

The identifier of the chat message.

content_parts: Array[ChatCompletionContentPartText { text, type } | ChatCompletionContentPartImage { image_url, type } ]

If a content parts array was provided, this is an array of text and image_url parts. Otherwise, null.

Accepts one of the following:
class ChatCompletionContentPartText { text, type }

Learn about text inputs.

text: String

The text content.

type: :text

The type of the content part.

class ChatCompletionContentPartImage { image_url, type }

Learn about image inputs.

image_url: { url, detail}
url: String

Either a URL of the image or the base64 encoded image data.

formaturi
detail: :auto | :low | :high

Specifies the detail level of the image. Learn more in the Vision guide.

Accepts one of the following:
:auto
:low
:high
type: :image_url

The type of the content part.

class ChatCompletionStreamOptions { include_obfuscation, include_usage }

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

include_obfuscation: bool

When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set include_obfuscation to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.

include_usage: bool

If set, an additional chunk will be streamed before the data: [DONE] message. The usage field on this chunk shows the token usage statistics for the entire request, and the choices field will always be an empty array.

All other chunks will also include a usage field, but with a null value. NOTE: If the stream is interrupted, you may not receive the final usage chunk which contains the total token usage for the request.

class 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.

content: String | Array[ChatCompletionContentPartText { text, type } ]

The contents of the system message.

Accepts one of the following:
String

The contents of the system message.

Array[ChatCompletionContentPartText { text, type } ]

An array of content parts with a defined type. For system messages, only type text is supported.

text: String

The text content.

type: :text

The type of the content part.

role: :system

The role of the messages author, in this case system.

name: String

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

class ChatCompletionTokenLogprob { token, bytes, logprob, top_logprobs }
token: String

The token.

bytes: Array[Integer]

A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.

logprob: Float

The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.

top_logprobs: Array[{ token, bytes, logprob}]

List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.

token: String

The token.

bytes: Array[Integer]

A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.

logprob: Float

The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.

ChatCompletionTool = ChatCompletionFunctionTool { function, type } | ChatCompletionCustomTool { custom, type }

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

Accepts one of the following:
class ChatCompletionFunctionTool { function, type }

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

function: FunctionDefinition { name, description, parameters, strict }
type: :function

The type of the tool. Currently, only function is supported.

class ChatCompletionCustomTool { custom, type }

A custom tool that processes input using a specified format.

custom: { name, description, format_}

Properties of the custom tool.

name: String

The name of the custom tool, used to identify it in tool calls.

description: String

Optional description of the custom tool, used to provide more context.

format_: { type} | { grammar, type}

The input format for the custom tool. Default is unconstrained text.

Accepts one of the following:
class Text { type }

Unconstrained free-form text.

type: :text

Unconstrained text format. Always text.

class Grammar { grammar, type }

A grammar defined by the user.

grammar: { definition, syntax}

Your chosen grammar.

definition: String

The grammar definition.

syntax: :lark | :regex

The syntax of the grammar definition. One of lark or regex.

Accepts one of the following:
:lark
:regex
type: :grammar

Grammar format. Always grammar.

type: :custom

The type of the custom tool. Always custom.

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.

Accepts one of the following:
Auto = :none | :auto | :required

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.

Accepts one of the following:
:none
:auto
:required
class ChatCompletionAllowedToolChoice { allowed_tools, type }

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

allowed_tools: ChatCompletionAllowedTools { mode, tools }

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

type: :allowed_tools

Allowed tool configuration type. Always allowed_tools.

class ChatCompletionNamedToolChoice { function, type }

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

function: { name}
name: String

The name of the function to call.

type: :function

For function calling, the type is always function.

class ChatCompletionNamedToolChoiceCustom { custom, type }

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

custom: { name}
name: String

The name of the custom tool to call.

type: :custom

For custom tool calling, the type is always custom.

class ChatCompletionToolMessageParam { content, role, tool_call_id }
content: String | Array[ChatCompletionContentPartText { text, type } ]

The contents of the tool message.

Accepts one of the following:
String

The contents of the tool message.

Array[ChatCompletionContentPartText { text, type } ]

An array of content parts with a defined type. For tool messages, only type text is supported.

text: String

The text content.

type: :text

The type of the content part.

role: :tool

The role of the messages author, in this case tool.

tool_call_id: String

Tool call that this message is responding to.

class ChatCompletionUserMessageParam { content, role, name }

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

content: String | Array[ChatCompletionContentPart]

The contents of the user message.

Accepts one of the following:
String

The text contents of the message.

Array[ChatCompletionContentPart]

An array of content parts with a defined type. Supported options differ based on the model being used to generate the response. Can contain text, image, or audio inputs.

Accepts one of the following:
class ChatCompletionContentPartText { text, type }

Learn about text inputs.

text: String

The text content.

type: :text

The type of the content part.

class ChatCompletionContentPartImage { image_url, type }

Learn about image inputs.

image_url: { url, detail}
url: String

Either a URL of the image or the base64 encoded image data.

formaturi
detail: :auto | :low | :high

Specifies the detail level of the image. Learn more in the Vision guide.

Accepts one of the following:
:auto
:low
:high
type: :image_url

The type of the content part.

class ChatCompletionContentPartInputAudio { input_audio, type }

Learn about audio inputs.

input_audio: { data, format_}
data: String

Base64 encoded audio data.

format_: :wav | :mp3

The format of the encoded audio data. Currently supports "wav" and "mp3".

Accepts one of the following:
:wav
:mp3
type: :input_audio

The type of the content part. Always input_audio.

class File { file, type }

Learn about file inputs for text generation.

file: { file_data, file_id, filename}
file_data: String

The base64 encoded file data, used when passing the file to the model as a string.

file_id: String

The ID of an uploaded file to use as input.

filename: String

The name of the file, used when passing the file to the model as a string.

type: :file

The type of the content part. Always file.

role: :user

The role of the messages author, in this case user.

name: String

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

class ChatCompletionAllowedTools { mode, tools }

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

mode: :auto | :required

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

auto allows the model to pick from among the allowed tools and generate a message.

required requires the model to call one or more of the allowed tools.

Accepts one of the following:
:auto
:required
tools: Array[Hash[Symbol, untyped]]

A list of tool definitions that the model should be allowed to call.

For the Chat Completions API, the list of tool definitions might look like:

[
  { "type": "function", "function": { "name": "get_weather" } },
  { "type": "function", "function": { "name": "get_time" } }
]

CompletionsMessages

Get chat messages
chat.completions.messages.list(completion_id, **kwargs) -> CursorPage<ChatCompletionStoreMessage { id, content_parts } >
GET/chat/completions/{completion_id}/messages