Optional
audioParameters for audio output. Only required when audio output is requested with modalities: ["audio"]
.
See: OpenAI's Audio Guide for more information.
Optional
cacheCaching configuration for a request. Cache is only supported for non-streaming requests.
Optional
frequencyA 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.
Optional
functionControls which (if any) function is called by the model.
"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.{"name": "my_function"}
forces the model to call that function. "none"
is the default when no functions are present. "auto"
is the default if functions are present.
Deprecated: function_call
has been deprecated by OpenAI in favor of tool_choice
.
Optional
functionsA list of functions the model may generate JSON inputs for.
Deprecated: functions
has been deprecated by OpenAI in favor of tools
.
Optional
headersOptional
logitModifies 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.
Optional
logprobsIndicates 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.
Optional
maxSpecifies an upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
Optional
maxSpecifies a 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.
Deprecated: max_tokens
has been deprecated by OpenAI in favor of max_completion_tokens
, and is not
compatible with o1
series models.
A list of messages comprising the chat conversation so far. Depending on the model you use, different
message types (modalities) are supported, like "text"
, "images"
, and "audio"
.
Optional
metadataContains developer-defined tags and values used for filtering completions.
Optional
modalitiesSpecifies the 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"]
). Some models can generate audio. For OpenAI, the
gpt-4o-audio-preview
model can be used to generate audio. To request that this model generate both text and
audio responses, you can use ["text", "audio"]
.
ID or alias of the model to forward the chat request to.
Optional
nSpecifies how many chat completion choices to generate for each input message.
Note: you will be charged based on the number of generated tokens across all choices, keep "n"
set to 1
to
minimize costs.
Optional
parallelSpecifies whether to enable parallel function calling during tool use.
Optional
predictionThe configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content.
Optional
presenceA 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.
Optional
reasoningConstrains effort on reasoning for reasoning models. For OpenAI, currently supported by o1
models only.
Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.
Optional
responseAn object specifying the format that the model must output.
{ "type": "json_schema", "json_schema": {...} }
enables Structured Outputs which ensures the
model will match your supplied JSON schema.{ "type": "json_object" }
enables JSON mode, which ensures 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"
is set to "length"
, which indicates the generation exceeded max_tokens
or the
conversation exceeded the max context length.
Optional
routerSpecifies model routing configurations for the request.
Optional
seedThe seed for the model request. For OpenAI, this feature is in Beta. If specified, OpenAI's system will make
a best effort attempt 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.
Optional
serviceThe service tier used for processing a request.
Optional
signalOptional
stopSpecifies up to 4 sequences where the API will stop generating further tokens.
Optional
storeIndicates whether to store the output of this chat completion request for use in OpenAI's model distillation or evals products.
Optional
streamIndicates whether to stream the model response to the user. 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.
Optional
streamOptions for streaming response. Only set this when you set stream
to true
.
Optional
temperatureSpecifies what sampling temperature to use. Higher values like 0.8
will make the output more random, while
lower values like 0.2
will make it more focused and deterministic.
Note: OpenAI generally recommends altering this or top_p
but not both.
Optional
toolControls 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.{"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.
Optional
toolsA list of tools the model may call. Currently, only functions are supported as tools. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.
Optional
topAn 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.
Optional
topPAn alternative to sampling with temperature
, called nucleus sampling, where the model considers the
results of the tokens with top_p
probability mass. Example: 0.1
means only the tokens comprising the top 10%
probability mass are considered.
Note: OpenAI generally recommends altering this or temperature
but not both.
Optional
userA unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
Parameters for the chat completion operation.