Creates a model response for the given chat conversation.
POST /chat/completions
Authorizations
Request Body required
object
A list of messages comprising the conversation so far. Example Python code.
object
The contents of the system message.
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, each can be of type text
or image_url
when passing in images. You can pass multiple images by adding multiple image_url
content parts. Image input is only supported when using the gpt-4-visual-preview
model.
object
The type of the content part.
The text content.
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.
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. Required unless tool_calls
or function_call
is specified.
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.
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.
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.
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.
The total length of input tokens and generated tokens is limited by the model’s context length. Example Python code for counting 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.
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.
An object specifying the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models newer than gpt-3.5-turbo-1106
.
Setting to { "type": "json_object" }
enables JSON mode, which guarantees the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly “stuck” request. Also note that the message content may be partially cut off if finish_reason="length"
, which indicates the generation exceeded max_tokens
or the conversation exceeded the max context length.
object
Must be one of text
or json_object
.
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.
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
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.
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 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.
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.
The Unix timestamp (in seconds) of when the chat completion was created.
The model used for the chat completion.
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).