CreateChatCompletionRequest class abstract

Request object for the Create chat completion endpoint.

Available extensions

• CreateChatCompletionRequestPatterns

Annotations

• @freezed

Constructors

CreateChatCompletionRequest({required ChatCompletionModel model, required List<ChatCompletionMessage> messages, @JsonKey.new(includeIfNull: false) bool? store, @JsonKey.new(name: 'reasoning_effort', includeIfNull: false, unknownEnumValue: JsonKey.nullForUndefinedEnumValue) ReasoningEffort? reasoningEffort, @JsonKey.new(includeIfNull: false) Map<String, String>? metadata, @JsonKey.new(name: 'frequency_penalty', includeIfNull: false) double? frequencyPenalty, @JsonKey.new(name: 'logit_bias', includeIfNull: false) Map<String, int>? logitBias, @JsonKey.new(includeIfNull: false) bool? logprobs, @JsonKey.new(name: 'top_logprobs', includeIfNull: false) int? topLogprobs, @JsonKey.new(name: 'max_tokens', includeIfNull: false) int? maxTokens, @JsonKey.new(name: 'max_completion_tokens', includeIfNull: false) int? maxCompletionTokens, @JsonKey.new(includeIfNull: false) int? n, @JsonKey.new(includeIfNull: false) List<ChatCompletionModality>? modalities, @JsonKey.new(includeIfNull: false) PredictionContent? prediction, @JsonKey.new(includeIfNull: false) ChatCompletionAudioOptions? audio, @JsonKey.new(name: 'presence_penalty', includeIfNull: false) double? presencePenalty, @JsonKey.new(name: 'web_search_options', includeIfNull: false) WebSearchOptions? webSearchOptions, @JsonKey.new(name: 'response_format', includeIfNull: false) ResponseFormat? responseFormat, @JsonKey.new(includeIfNull: false) int? seed, @JsonKey.new(name: 'service_tier', includeIfNull: false, unknownEnumValue: JsonKey.nullForUndefinedEnumValue) CreateChatCompletionRequestServiceTier? serviceTier, @JsonKey.new(includeIfNull: false) ChatCompletionStop? stop, @JsonKey.new(includeIfNull: false) @Default.new(false) bool? stream, @JsonKey.new(name: 'stream_options', includeIfNull: false) ChatCompletionStreamOptions? streamOptions, @JsonKey.new(includeIfNull: false) double? temperature, @JsonKey.new(name: 'top_p', includeIfNull: false) double? topP, @JsonKey.new(name: 'top_k', includeIfNull: false) int? topK, @JsonKey.new(name: 'min_p', includeIfNull: false) double? minP, @JsonKey.new(name: 'top_a', includeIfNull: false) double? topA, @JsonKey.new(name: 'repetition_penalty', includeIfNull: false) double? repetitionPenalty, @JsonKey.new(includeIfNull: false) List<ChatCompletionTool>? tools, @JsonKey.new(name: 'tool_choice', includeIfNull: false) ChatCompletionToolChoiceOption? toolChoice, @JsonKey.new(name: 'parallel_tool_calls', includeIfNull: false) bool? parallelToolCalls, @JsonKey.new(includeIfNull: false) String? user, @JsonKey.new(name: 'function_call', includeIfNull: false) ChatCompletionFunctionCall? functionCall, @JsonKey.new(includeIfNull: false) List<FunctionObject>? functions, @JsonKey.new(includeIfNull: false, unknownEnumValue: JsonKey.nullForUndefinedEnumValue) Verbosity? verbosity, @JsonKey.new(includeIfNull: false) CreateChatCompletionRequestReasoning? reasoning, @JsonKey.new(includeIfNull: false) OpenRouterProviderPreferences? provider, @JsonKey.new(includeIfNull: false) List<String>? models, @JsonKey.new(includeIfNull: false, unknownEnumValue: JsonKey.nullForUndefinedEnumValue) CreateChatCompletionRequestRoute? route, @JsonKey.new(includeIfNull: false) List<String>? transforms, @JsonKey.new(includeIfNull: false) OpenRouterUsageConfig? usage})

Factory constructor for CreateChatCompletionRequest

const

factory

CreateChatCompletionRequest.fromJson(Map<String, dynamic> json)

Object construction from a JSON representation

factory

Properties

audio → ChatCompletionAudioOptions?

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.

no setter, inherited

copyWith → $CreateChatCompletionRequestCopyWith<CreateChatCompletionRequest>

Create a copy of CreateChatCompletionRequest with the given fields replaced by the non-null parameter values.

no setter, inherited

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.

no setter, inherited

functionCall → ChatCompletionFunctionCall?

Deprecated in favor of tool_choice.

no setter, inherited

functions → List<FunctionObject>?

Deprecated in favor of tools.

no setter, inherited

hashCode → int

The hash code for this object.

no setter, inherited

logitBias → Map<String, int>?

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.

no setter, inherited

logprobs → 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.

no setter, inherited

maxCompletionTokens → int?

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

no setter, inherited

maxTokens → int?

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.

no setter, inherited

messages → List<ChatCompletionMessage>

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.

no setter, inherited

metadata → Map<String, String>?

Developer-defined tags and values used for filtering completions in the dashboard.

no setter, inherited

minP → double?

Minimum probability threshold for token selection, relative to the probability of the most likely token. Only tokens with probability >= min_p * max_prob are considered.

no setter, inherited

modalities → List<ChatCompletionModality>?

A list of modalities that the model may use to generate the completion.

no setter, inherited

model → ChatCompletionModel

ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.

no setter, inherited

models → List<String>?

Multiple model options for automatic fallback. If the primary model's providers are down, rate-limited, or refuse due to content moderation, automatically tries other models.

no setter, inherited

n → int?

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.

no setter, inherited

parallelToolCalls → bool?

Whether to enable parallel function calling during tool use.

no setter, inherited

prediction → PredictionContent?

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.

no setter, inherited

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.

no setter, inherited

provider → OpenRouterProviderPreferences?

Provider routing preferences for controlling how requests are routed to different model providers.

no setter, inherited

reasoning → CreateChatCompletionRequestReasoning?

Reasoning configuration for controlling how the model generates and exposes its chain-of-thought reasoning.

no setter, inherited

reasoningEffort → ReasoningEffort?

Constrains effort on reasoning for reasoning models. Currently supported values are minimal, low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

no setter, inherited

repetitionPenalty → double?

Reduces repetition of tokens from the input. A value of 1.0 means no penalty. Higher values (up to 2.0) more strongly discourage repetition.

no setter, inherited

responseFormat → ResponseFormat?

An object specifying the format that the model must output.

no setter, inherited

route → CreateChatCompletionRequestRoute?

Routing strategy to use with the models array. Set to "fallback" to enable model fallback functionality.

no setter, inherited

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

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.

no setter, inherited

serviceTier → CreateChatCompletionRequestServiceTier?

Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the Flex Processing service:

no setter, inherited

stop → ChatCompletionStop?

Up to 4 sequences where the API will stop generating further tokens.

no setter, inherited

store → bool?

Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

no setter, inherited

stream → bool?

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.

no setter, inherited

streamOptions → ChatCompletionStreamOptions?

Options for streaming response. Only set this when you set stream: true.

no setter, inherited

temperature → double?

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.

no setter, inherited

toolChoice → ChatCompletionToolChoiceOption?

Controls 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. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

no setter, inherited

tools → List<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.

no setter, inherited

topA → double?

Consider only tokens with "sufficiently high" probabilities based on the probability of the most likely token. Functions as a dynamic top-p filter.

no setter, inherited

topK → int?

Sample from the k most likely next tokens at each step. Lower k focuses on higher probability tokens, while higher k allows more diversity.

no setter, inherited

topLogprobs → int?

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.

no setter, inherited

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. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

no setter, inherited

transforms → List<String>?

List of prompt transforms applied to messages before sending to the model. Transformations are applied in order.

no setter, inherited

usage → OpenRouterUsageConfig?

Usage accounting configuration for detailed token usage information.

no setter, inherited

user → String?

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

no setter, inherited

verbosity → Verbosity?

Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.

no setter, inherited

webSearchOptions → WebSearchOptions?

This tool searches the web for relevant results to use in a response.

no setter, inherited

Methods

map<TResult extends Object?>(TResult $default(_CreateChatCompletionRequest value)) → TResult

Available on CreateChatCompletionRequest, provided by the CreateChatCompletionRequestPatterns extension

A switch-like method, using callbacks.

mapOrNull<TResult extends Object?>(TResult? $default(_CreateChatCompletionRequest value)?) → TResult?

Available on CreateChatCompletionRequest, provided by the CreateChatCompletionRequestPatterns extension

A variant of map that fallback to returning null.

maybeMap<TResult extends Object?>(TResult $default(_CreateChatCompletionRequest value)?, {required TResult orElse()}) → TResult

Available on CreateChatCompletionRequest, provided by the CreateChatCompletionRequestPatterns extension

A variant of map that fallback to returning orElse.

maybeWhen<TResult extends Object?>(TResult $default(ChatCompletionModel model, List<ChatCompletionMessage> messages, bool? store, ReasoningEffort? reasoningEffort, Map<String, String>? metadata, double? frequencyPenalty, Map<String, int>? logitBias, bool? logprobs, int? topLogprobs, int? maxTokens, int? maxCompletionTokens, int? n, List<ChatCompletionModality>? modalities, PredictionContent? prediction, ChatCompletionAudioOptions? audio, double? presencePenalty, WebSearchOptions? webSearchOptions, ResponseFormat? responseFormat, int? seed, CreateChatCompletionRequestServiceTier? serviceTier, ChatCompletionStop? stop, bool? stream, ChatCompletionStreamOptions? streamOptions, double? temperature, double? topP, int? topK, double? minP, double? topA, double? repetitionPenalty, List<ChatCompletionTool>? tools, ChatCompletionToolChoiceOption? toolChoice, bool? parallelToolCalls, String? user, ChatCompletionFunctionCall? functionCall, List<FunctionObject>? functions, Verbosity? verbosity, CreateChatCompletionRequestReasoning? reasoning, OpenRouterProviderPreferences? provider, List<String>? models, CreateChatCompletionRequestRoute? route, List<String>? transforms, OpenRouterUsageConfig? usage)?, {required TResult orElse()}) → TResult

Available on CreateChatCompletionRequest, provided by the CreateChatCompletionRequestPatterns extension

A variant of when that fallback to an orElse callback.

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toJson() → Map<String, dynamic>

Serializes this CreateChatCompletionRequest to a JSON map.

inherited

toMap() → Map<String, dynamic>

Map representation of object (not serialized)

toString() → String

A string representation of this object.

inherited

validateSchema() → String?

Perform validations on the schema property values

when<TResult extends Object?>(TResult $default(ChatCompletionModel model, List<ChatCompletionMessage> messages, bool? store, ReasoningEffort? reasoningEffort, Map<String, String>? metadata, double? frequencyPenalty, Map<String, int>? logitBias, bool? logprobs, int? topLogprobs, int? maxTokens, int? maxCompletionTokens, int? n, List<ChatCompletionModality>? modalities, PredictionContent? prediction, ChatCompletionAudioOptions? audio, double? presencePenalty, WebSearchOptions? webSearchOptions, ResponseFormat? responseFormat, int? seed, CreateChatCompletionRequestServiceTier? serviceTier, ChatCompletionStop? stop, bool? stream, ChatCompletionStreamOptions? streamOptions, double? temperature, double? topP, int? topK, double? minP, double? topA, double? repetitionPenalty, List<ChatCompletionTool>? tools, ChatCompletionToolChoiceOption? toolChoice, bool? parallelToolCalls, String? user, ChatCompletionFunctionCall? functionCall, List<FunctionObject>? functions, Verbosity? verbosity, CreateChatCompletionRequestReasoning? reasoning, OpenRouterProviderPreferences? provider, List<String>? models, CreateChatCompletionRequestRoute? route, List<String>? transforms, OpenRouterUsageConfig? usage)) → TResult

Available on CreateChatCompletionRequest, provided by the CreateChatCompletionRequestPatterns extension

A switch-like method, using callbacks.

whenOrNull<TResult extends Object?>(TResult? $default(ChatCompletionModel model, List<ChatCompletionMessage> messages, bool? store, ReasoningEffort? reasoningEffort, Map<String, String>? metadata, double? frequencyPenalty, Map<String, int>? logitBias, bool? logprobs, int? topLogprobs, int? maxTokens, int? maxCompletionTokens, int? n, List<ChatCompletionModality>? modalities, PredictionContent? prediction, ChatCompletionAudioOptions? audio, double? presencePenalty, WebSearchOptions? webSearchOptions, ResponseFormat? responseFormat, int? seed, CreateChatCompletionRequestServiceTier? serviceTier, ChatCompletionStop? stop, bool? stream, ChatCompletionStreamOptions? streamOptions, double? temperature, double? topP, int? topK, double? minP, double? topA, double? repetitionPenalty, List<ChatCompletionTool>? tools, ChatCompletionToolChoiceOption? toolChoice, bool? parallelToolCalls, String? user, ChatCompletionFunctionCall? functionCall, List<FunctionObject>? functions, Verbosity? verbosity, CreateChatCompletionRequestReasoning? reasoning, OpenRouterProviderPreferences? provider, List<String>? models, CreateChatCompletionRequestRoute? route, List<String>? transforms, OpenRouterUsageConfig? usage)?) → TResult?

Available on CreateChatCompletionRequest, provided by the CreateChatCompletionRequestPatterns extension

A variant of when that fallback to returning null

Operators

operator ==(Object other) → bool

The equality operator.

inherited

Constants

frequencyPenaltyMaxValue → const double

frequencyPenaltyMinValue → const double

Validation constants

minPMaxValue → const double

minPMinValue → const double

nMaxValue → const int

nMinValue → const int

presencePenaltyMaxValue → const double

presencePenaltyMinValue → const double

propertyNames → const List<String>

List of all property names of schema

repetitionPenaltyMaxValue → const double

repetitionPenaltyMinValue → const double

temperatureMaxValue → const double

temperatureMinValue → const double

topAMaxValue → const double

topAMinValue → const double

topKMinValue → const int

topLogprobsMaxValue → const int

topLogprobsMinValue → const int

topPMaxValue → const double

topPMinValue → const double