Responses#

Executes a single stateless request to the Responses API and returns the full response along with convenient extracted fields.

Text	[Text] Simple user text; required if Input is not provided. The client converts it into an input element with the role of user.
Input	[Array of objects] Ready elements of the Responses API; if provided, they take precedence over Text.
Model	Model provider selection
CustomModelName	[Text] Optional name of the Sherpa AI Server model; if empty, the model selects the server.
Temperature	[Number] Generation temperature; default value is 0.7.
TopP	[Number] Nucleus sampling threshold; empty value is not sent.
MaxTokens	[Number] Maximum number of response tokens
Tools	[Array of objects] Descriptions of available model tools.
ToolChoice	[Text \| object] Tool selection rule.
ResponseFormat	[Object] Required response format of the model.
Timeout	[Number] Timeout for waiting for a response from the model in seconds; default value is 300.
OutputText	[Text] First final text from output; remains empty if there is no text element.
ResponseId	[Text] Response identifier of the Responses API.
Status	[Text] Status of the model response.
Response	Full typed response of the Responses API.
Output	All output elements, including text, tool calls, and other types.
Usage	Token usage data.
Error Handling Level	Selection of error handling level. Possible values: "Default" - default; "Ignore" - errors are ignored; "Handle" - errors are handled. If "Default" is selected, the value from the "Start" block of this diagram will be used.
Message Level	Selection of the message level that blocks will output during operation. Possible values: "Default" - default; "Release" - output is disabled; "Debug" - main information output; "Detailed" - detailed information output. If "Default" is selected, the value from the "Start" block of this diagram will be used.
Error Text	[Text] Returns detailed information about the error in case of incorrect execution of the block's work.