Interface ChatInputMulti

ChatInputMulti represents the full potential input options for chat.

interface ChatInputMulti {
    frequencyPenalty?: number;
    inputExtension?: InputExtension;
    logitBias?: {
        [token: string]: number;
    };
    maxCompletionTokens?: number;
    maxTokens?: number;
    messages: ChatInputMessage[];
    model: string;
    outputExtension?: OutputExtension;
    parallelToolCalls?: boolean;
    presencePenalty?: number;
    reasoningEffort?: string;
    stop?: string | string[];
    temperature?: number;
    toolChoice?: string | ToolChoiceFunction;
    tools?: Tool[];
    topK?: number;
    topP?: number;
}

Properties

frequencyPenalty? inputExtension? logitBias? maxCompletionTokens? maxTokens? messages model outputExtension? parallelToolCalls? presencePenalty? reasoningEffort? stop? temperature? toolChoice? tools? topK? topP?

Properties

Optional frequencyPenalty

frequencyPenalty?: number

frequencyPenalty represents a value between -2.0 and 2.0 to penalize tokens based on frequency.

Optional inputExtension

inputExtension?: InputExtension

inputExtension represents a set of optional pre-processing integrations.

Optional logitBias

logitBias?: {
    [token: string]: number;
}

logitBias modifies the likelihood of specified tokens appearing in a response.

Type declaration

  • [token: string]: number

Optional maxCompletionTokens

maxCompletionTokens?: number

maxCompletionTokens represents the maximum number of tokens in the generated completion.

Optional maxTokens

maxTokens?: number

maxTokens represents the max number of tokens to return.

Deprecated

Use maxCompletionTokens instead.

messages

messages: ChatInputMessage[]

messages represents the set of messages to process.

model

model: string

model represents the model to use.

Optional outputExtension

outputExtension?: OutputExtension

outputExtension represents a set of optional post-processing integrations.

Optional parallelToolCalls

parallelToolCalls?: boolean

parallelToolCalls represents whether to enable parallel function calling during tool use.

Optional presencePenalty

presencePenalty?: number

presencePenalty represents a value between -2.0 and 2.0 to penalize tokens based on presence.

Optional reasoningEffort

reasoningEffort?: string

reasoningEffort constrains effort on reasoning for reasoning models.

Optional stop

stop?: string | string[]

stop represents one or more sequences where the API will stop generating tokens.

Optional temperature

temperature?: number

temperature represents the randomness in GPT's output.

Optional toolChoice

toolChoice?: string | ToolChoiceFunction

toolChoice represents whether to enable tool calling and which tool to use.

Optional tools

tools?: Tool[]

tools represents an array of tools the model may call.

Optional topK

topK?: number

topK represents the variability of the generated text.

Optional topP

topP?: number

topP represents the diversity of the generated text.

Settings

Member Visibility

Theme

On This Page

frequencyPenaltyinputExtensionlogitBiasmaxCompletionTokensmaxTokensmessagesmodeloutputExtensionparallelToolCallspresencePenaltyreasoningEffortstoptemperaturetoolChoicetoolstopKtopP