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
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.
object
The contents of the system message.
An array of content parts with a defined type. For system messages, only type text
is supported.
Learn about text inputs.
object
The type of the content part.
The text content.
The role of the messages author, in this case system
.
An optional name for the participant. Provides the model information to differentiate between participants of the same role.
object
The text contents of the message.
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.
Learn about text inputs.
object
The type of the content part.
The text content.
Learn about image inputs.
object
The type of the content part.
object
Either a URL of the image or the base64 encoded image data.
Specifies the detail level of the image. Learn more in the Vision guide.
Learn about audio inputs.
object
The type of the content part. Always input_audio
.
object
Base64 encoded audio data.
The format of the encoded audio data. Currently supports “wav” and “mp3”.
The role of the messages author, in this case user
.
An optional name for the participant. Provides the model information to differentiate between participants of the same role.
object
The contents of the assistant message.
An array of content parts with a defined type. Can be one or more of type text
, or exactly one of type refusal
.
Learn about text inputs.
object
The type of the content part.
The text content.
object
The type of the content part.
The refusal message generated by the model.
The refusal message by the assistant.
The role of the messages author, in this case 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.
object
Unique identifier for a previous audio response from the model.
The tool calls generated by the model, such as function calls.
object
The ID of the tool call.
The type of the tool. Currently, only function
is supported.
The function that the model called.
object
The name of the function to call.
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.
Deprecated and replaced by tool_calls
. The name and arguments of a function that should be called, as generated by the model.
object
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.
The name of the function to call.
object
The role of the messages author, in this case tool
.
The contents of the tool message.
An array of content parts with a defined type. For tool messages, only type text
is supported.
Learn about text inputs.
object
The type of the content part.
The text content.
Tool call that this message is responding to.
object
The role of the messages author, in this case function
.
The contents of the function message.
The name of the function to call.
Whether or not to store the output of this chat completion request for use in our model distillation or evals products.
Developer-defined tags and values used for filtering completions in the dashboard.
object
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.
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
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
.
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.
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.
An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
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.
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"]
Parameters for audio output. Required when audio output is requested with
modalities: ["audio"]
. Learn more.
object
Specifies the voice type. Supported voices are alloy
, echo
,
fable
, onyx
, nova
, and shimmer
.
Specifies the output audio format. Must be one of wav
, mp3
, flac
,
opus
, or pcm16
.
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.
object
The type of response format being defined: text
object
The type of response format being defined: json_object
object
The type of response format being defined: json_schema
object
A description of what the response format is for, used by the model to determine how to respond in the format.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
The schema for the response format, described as a JSON Schema object.
object
Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema
field. Only a subset of JSON Schema is supported when strict
is true
. To learn more, read the Structured Outputs guide.
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.
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.
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.
Options for streaming response. Only set this when you set stream: true
.
object
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.
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.
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.
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.
object
The type of the tool. Currently, only function
is supported.
object
A description of what the function does, used by the model to choose when and how to call the function.
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.
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
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.
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.
Specifies a tool the model should use. Use to force the model to call a specific function.
object
The type of the tool. Currently, only function
is supported.
object
The name of the function to call.
Whether to enable parallel function calling during tool use.
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
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.
Specifying a particular function via {"name": "my_function"}
forces the model to call that function.
object
The name of the function to call.
Deprecated in favor of tools
.
A list of functions the model may generate JSON inputs for.
object
A description of what the function does, used by the model to choose when and how to call the function.
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.
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
Responses
200
OK
Represents a chat completion response returned by model, based on the provided input.
object
A unique identifier for the chat completion.
A list of chat completion choices. Can be more than one if n
is greater than 1.
object
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.
The index of the choice in the list of choices.
A chat completion message generated by the model.
object
The contents of the message.
The refusal message generated by the model.
The tool calls generated by the model, such as function calls.
object
The ID of the tool call.
The type of the tool. Currently, only function
is supported.
The function that the model called.
object
The name of the function to call.
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.
The role of the author of this message.
Deprecated and replaced by tool_calls
. The name and arguments of a function that should be called, as generated by the model.
object
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.
The name of the function to call.
If the audio output modality is requested, this object contains data about the audio response from the model. Learn more.
object
Unique identifier for this audio response.
The Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations.
Base64 encoded audio bytes generated by the model, in the format specified in the request.
Transcript of the audio generated by the model.
Log probability information for the choice.
object
A list of message content tokens with log probability information.
object
The token.
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.
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.
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.
object
The token.
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.
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.
A list of message refusal tokens with log probability information.
object
The token.
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.
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.
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.
object
The token.
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.
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.
The Unix timestamp (in seconds) of when the chat completion was created.
The model used for the chat completion.
The service tier used for processing the request. This field is only included if the service_tier
parameter is specified in the request.
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.
The object type, which is always chat.completion
.
Usage statistics for the completion request.
object
Number of tokens in the generated completion.
Number of tokens in the prompt.
Total number of tokens used in the request (prompt + completion).
Breakdown of tokens used in a completion.
object
Audio input tokens generated by the model.
Tokens generated by the model for reasoning.
Breakdown of tokens used in the prompt.
object
Audio input tokens present in the prompt.
Cached tokens present in the prompt.