pub struct CreateChatCompletionRequest {Show 31 fields
pub metadata: Option<Metadata>,
pub service_tier: Option<ServiceTier>,
pub temperature: Option<f32>,
pub top_p: Option<f32>,
pub user: Option<String>,
pub audio: Option<CreateChatCompletionRequestAudio>,
pub frequency_penalty: Option<f32>,
pub function_call: Option<Value>,
pub functions: Option<Vec<ChatCompletionFunctions>>,
pub logit_bias: Option<HashMap<String, i32>>,
pub logprobs: Option<bool>,
pub max_completion_tokens: Option<i32>,
pub max_tokens: Option<i32>,
pub messages: Vec<ChatCompletionRequestMessage>,
pub modalities: Option<ResponseModalities>,
pub model: ModelIdsShared,
pub n: Option<i32>,
pub parallel_tool_calls: Option<ParallelToolCalls>,
pub prediction: Option<Value>,
pub presence_penalty: Option<f32>,
pub reasoning_effort: Option<ReasoningEffort>,
pub response_format: Option<Value>,
pub seed: Option<i32>,
pub stop: Option<StopConfiguration>,
pub store: Option<bool>,
pub stream: Option<bool>,
pub stream_options: Option<ChatCompletionStreamOptions>,
pub tool_choice: Option<ChatCompletionToolChoiceOption>,
pub tools: Option<Vec<ChatCompletionTool>>,
pub top_logprobs: Option<i32>,
pub web_search_options: Option<WebSearch>,
}Fields§
§metadata: Option<Metadata>§service_tier: Option<ServiceTier>§temperature: Option<f32>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.
top_p: Option<f32>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.
user: Option<String>A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
audio: Option<CreateChatCompletionRequestAudio>§frequency_penalty: Option<f32>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.
function_call: Option<Value>Deprecated in favor of tool_choice. Controls 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. Specifying a particular function via {\"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.
functions: Option<Vec<ChatCompletionFunctions>>Deprecated in favor of tools. A list of functions the model may generate JSON inputs for.
logit_bias: Option<HashMap<String, i32>>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.
logprobs: Option<bool>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.
max_completion_tokens: Option<i32>An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
max_tokens: Option<i32>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 o-series models.
messages: Vec<ChatCompletionRequestMessage>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.
modalities: Option<ResponseModalities>§model: ModelIdsSharedModel ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.
n: Option<i32>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.
parallel_tool_calls: Option<ParallelToolCalls>§prediction: Option<Value>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.
presence_penalty: Option<f32>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.
reasoning_effort: Option<ReasoningEffort>§response_format: Option<Value>An object specifying the format that the model must output. Setting to { \"type\": \"json_schema\", \"json_schema\": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide. Setting to { \"type\": \"json_object\" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
seed: Option<i32>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.
stop: Option<StopConfiguration>§store: Option<bool>Whether or not to store the output of this chat completion request for use in our model distillation or evals products.
stream: Option<bool>If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information, along with the streaming responses guide for more information on how to handle the streaming events.
stream_options: Option<ChatCompletionStreamOptions>§tool_choice: Option<ChatCompletionToolChoiceOption>§tools: Option<Vec<ChatCompletionTool>>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.
top_logprobs: Option<i32>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.
web_search_options: Option<WebSearch>