OpenAIChatOptions class

Generation options to pass into the Chat Model.

Inheritance
Annotations
  • @immutable

Constructors

OpenAIChatOptions({double? frequencyPenalty, Map<String, int>? logitBias, int? maxTokens, int? n, double? presencePenalty, dynamic responseFormat, int? seed, List<String>? stop, double? temperature, double? topP, bool? parallelToolCalls, ChatOpenAIServiceTier? serviceTier, String? user, StreamOptions? streamOptions, bool? logprobs, int? topLogprobs, ReasoningEffort? reasoningEffort, Verbosity? verbosity, Prediction? prediction, List<ChatModality>? modalities, ChatAudioConfig? audio, WebSearchOptions? webSearchOptions, bool? store, Map<String, dynamic>? metadata, String? promptCacheKey, PromptCacheRetention? promptCacheRetention, String? safetyIdentifier})
Creates a new chat openai options instance.
const

Properties

audio → ChatAudioConfig?
Audio output configuration (voice and format). Required when modalities includes ChatModality.audio.
final
frequencyPenalty → double?
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.
final
hashCode → int
The hash code for this object.
no setterinherited
logitBias → Map<String, int>?
Modify the likelihood of specified tokens appearing in the completion.
final
logprobs → bool?
Whether to return log probabilities of the output tokens or not.
final
maxTokens → int?
The maximum number of tokens to generate in the chat completion. Defaults to inf.
final
metadata → Map<String, dynamic>?
Custom metadata to attach to the request.
final
modalities → List<ChatModality>?
Output modalities to request (e.g. text, audio).
final
n → int?
How many chat completion choices to generate for each input message.
final
parallelToolCalls → bool?
Whether to enable parallel tool calling during tool use. By default, it is enabled.
final
prediction → Prediction?
Predicted output for faster responses when high confidence in the response content. Works best with gpt-4o and gpt-4.1 models.
final
presencePenalty → double?
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.
final
promptCacheKey → String?
Prompt cache key for optimizing cache hit rates.
final
promptCacheRetention → PromptCacheRetention?
Retention policy for the prompt cache.
final
reasoningEffort → ReasoningEffort?
Controls reasoning effort for reasoning models (o1, o3, o4-mini).
final
responseFormat → dynamic
An object specifying the format that the model must output.
final
runtimeType → Type
A representation of the runtime type of the object.
no setterinherited
safetyIdentifier → String?
A stable identifier for detecting usage policy violations.
final
seed → int?
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.
final
serviceTier → ChatOpenAIServiceTier?
Specifies the latency tier to use for processing the request. This is relevant for customers subscribed to the scale tier service.
final
stop → List<String>?
Up to 4 sequences where the API will stop generating further tokens.
final
store → bool?
Whether to store this completion for model improvements.
final
streamOptions → StreamOptions?
Stream options for OpenAI chat completions.
final
temperature → double?
What sampling temperature to use, between 0 and 2.
final
topLogprobs → int?
An integer between 0 and 20 specifying the number of most likely tokens to return at each token position.
final
topP → double?
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
final
user → String?
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.
final
verbosity → Verbosity?
Controls the verbosity of the model's response.
final
webSearchOptions → WebSearchOptions?
Web search options for including web results in the response.
final

Methods

noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
toString() → String
A string representation of this object.
inherited

Operators

operator ==(Object other) → bool
The equality operator.
inherited