Generate Response

This action generates a response to the provided message with an AI model.

Action Settings

Setting Description
Instructions String. A system message inserted into the model's context. Alternatively, instructions describing the desired change or result.
Model Enum. The ID of the model to use.
Temperature Double. The sampling temperature to use, between 0 and 2. Higher values will make the result more random, lower values - more determined.
Top P Double. This parameter is used as an alternative to the Temperature parameter. It is a number from 0 to 1.
Max Output Tokens Int32. The maximum number of output tokens that can be generated.
Max Tool Calls Int32. The maximum number of total calls to built-in tools.
Store Boolean. Determines whether to store the generated response to retrieve it later via API.
Reasoning Effort Enum. The effort the model should put into reasoning.

Action Parameters

Parameter Description
Message String. The prompt for the AI. This parameter is required.
PreviousResponseId String. The unique ID of the previous response to the model. You can use it to create multi-turn conversations.

Result

The action returns the following result fields: Response_Result, Response_Reasoning, Response_Id, Response_Status, Response_Error, Response_Object, Response_CreatedAt, Response_CompletedAt, Response_IncompleteDetails, Response_Temperature, Response_TopP, Response_MaxOutputTokens, Response_MaxTollCalls, Response_PreviousResponseId, Response_Store, Response_Model, Response_TextFormatType, Response_TextVerbosity, Response_ReasoningEffort, Response_ReasoningSummary, Response_Truncation, Response_SafetyIdentifier, Response_ParallelToolCalls, Response_ToolChoice, Response_Tools, Response_ServiceTier, Response_UsageInputTokens, Response_UsageInputTokensDetailsCachedTokens, Response_UsageOutputTokens, Response_UsageTotalTokens, Response_UsageNumSourcesUsed, Response_UsageNumServerSideToolsUsed, Response_UsageCostInUsdTicks, Response_UsageOutputTokensDetailsReasoningTokens.