Skip to content

Creates a model response for the given chat conversation. Learn more in the [text generation](/docs/guides/text-generation), [vision](/docs/guides/vision), and [audio](/docs/guides/audio) guides.

POST
/chat/completions

Authorizations

Request Body required

object
messages
required

A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.

Array
>= 1 items
One of:
object
content
required
One of:

The contents of the system message.

string
role
required

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

string
Allowed values: system
name

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

string
model
required
Any of:
string
store

Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

boolean
nullable
metadata

Developer-defined tags and values used for filtering completions in the dashboard.

object
key
additional properties
string
frequency_penalty

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.

See more information about frequency and presence penalties.

number
nullable >= -2 <= 2
logit_bias

Modify the likelihood of specified tokens appearing in the completion.

Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

object
key
additional properties
integer
logprobs

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

boolean
nullable
top_logprobs

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

integer
nullable <= 20
max_tokens

The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

This value is now deprecated in favor of max_completion_tokens, and is not compatible with o1 series models.

integer
nullable
max_completion_tokens

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

integer
nullable
n

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

integer
default: 1 nullable >= 1 <= 128
1
modalities

Output 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"]

Array<string>
nullable
Allowed values: text audio
audio

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

object
voice
required

Specifies the voice type. Supported voices are alloy, echo, fable, onyx, nova, and shimmer.

string
Allowed values: alloy echo fable onyx nova shimmer
format
required

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

string
Allowed values: wav mp3 flac opus pcm16
presence_penalty

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.

See more information about frequency and presence penalties.

number
nullable >= -2 <= 2
response_format
One of:
object
type
required

The type of response format being defined: text

string
Allowed values: text
seed

This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

integer
nullable >= -9223372036854776000 <= 9223372036854776000
service_tier

Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:

  • If set to ‘auto’, and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted.
  • If set to ‘auto’, and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.
  • If set to ‘default’, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.
  • When not set, the default behavior is ‘auto’.

When this parameter is set, the response body will include the service_tier utilized.

string
default: auto nullable
Allowed values: auto default
stop
One of:
string
nullable
stream

If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

boolean
nullable
stream_options

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

object
include_usage

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.

boolean
temperature

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

We generally recommend altering this or top_p but not both.

number
default: 1 nullable <= 2
1
top_p

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

number
default: 1 nullable <= 1
1
tools

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.

Array<object>
object
type
required

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

string
Allowed values: function
function
required
object
description

A description of what the function does, used by the model to choose when and how to call the function.

string
name
required

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

string
parameters

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

object
key
additional properties
any
strict

Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.

boolean
nullable
tool_choice
One of:

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.

string
Allowed values: none auto required
parallel_tool_calls

Whether to enable parallel function calling during tool use.

boolean
default: true
user

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

string
user-1234
function_call
One of:

none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function.

string
Allowed values: none auto
functions

Deprecated in favor of tools.

A list of functions the model may generate JSON inputs for.

Array<object>
>= 1 items <= 128 items
object
description

A description of what the function does, used by the model to choose when and how to call the function.

string
name
required

The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

string
parameters

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.

Omitting parameters defines a function with an empty parameter list.

object
key
additional properties
any

Responses

200

OK

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

object
id
required

A unique identifier for the chat completion.

string
choices
required

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

Array<object>
object
finish_reason
required

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.

string
Allowed values: stop length tool_calls content_filter function_call
index
required

The index of the choice in the list of choices.

integer
message
required

A chat completion message generated by the model.

object
content
required

The contents of the message.

string
nullable
refusal
required

The refusal message generated by the model.

string
nullable
tool_calls

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

Array<object>
object
id
required

The ID of the tool call.

string
type
required

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

string
Allowed values: function
function
required

The function that the model called.

object
name
required

The name of the function to call.

string
arguments
required

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.

string
role
required

The role of the author of this message.

string
Allowed values: assistant
function_call

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

object
arguments
required

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.

string
name
required

The name of the function to call.

string
audio

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

object
id
required

Unique identifier for this audio response.

string
expires_at
required

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

integer
data
required

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

string
transcript
required

Transcript of the audio generated by the model.

string
logprobs
required

Log probability information for the choice.

object
content
required

A list of message content tokens with log probability information.

Array<object>
nullable
object
token
required

The token.

string
logprob
required

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.

number
bytes
required

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.

Array<integer>
nullable
top_logprobs
required

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.

Array<object>
object
token
required

The token.

string
logprob
required

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.

number
bytes
required

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.

Array<integer>
nullable
refusal
required

A list of message refusal tokens with log probability information.

Array<object>
nullable
object
token
required

The token.

string
logprob
required

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.

number
bytes
required

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.

Array<integer>
nullable
top_logprobs
required

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.

Array<object>
object
token
required

The token.

string
logprob
required

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.

number
bytes
required

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.

Array<integer>
nullable
created
required

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

integer
model
required

The model used for the chat completion.

string
service_tier

The service tier used for processing the request. This field is only included if the service_tier parameter is specified in the request.

string
nullable
Allowed values: scale default
scale
system_fingerprint

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.

string
object
required

The object type, which is always chat.completion.

string
Allowed values: chat.completion
usage

Usage statistics for the completion request.

object
completion_tokens
required

Number of tokens in the generated completion.

integer
prompt_tokens
required

Number of tokens in the prompt.

integer
total_tokens
required

Total number of tokens used in the request (prompt + completion).

integer
completion_tokens_details

Breakdown of tokens used in a completion.

object
audio_tokens

Audio input tokens generated by the model.

integer
reasoning_tokens

Tokens generated by the model for reasoning.

integer
prompt_tokens_details

Breakdown of tokens used in the prompt.

object
audio_tokens

Audio input tokens present in the prompt.

integer
cached_tokens

Cached tokens present in the prompt.

integer