Response
A request to the Responses API.
The conversation travels in input, either as one user message (ResponseInput.Text) or as a list of items (ResponseInput.Items) — the API is stateless, so the list carries the whole history every turn. At least one of input and instructions must be present.
Build one through ResponseParams.createRequest or the createResponse { } DSL rather than by hand when more than the input varies.
See also
Constructors
Creates a request whose input is a single user message.
Creates a request whose input is a list of conversation items.
Types
DSL for building the multimodal content of a single message or tool output.
DSL for building the input of a Responses API call.
Builder for streaming Responses API requests.
Properties
The conversation, as one user message or as a list of items; null when the request is driven by instructions alone.
System-level instruction, inserted as the first system message of the model's context.
Ceiling on the tokens generated for the response, counting both the visible answer and the reasoning.
Thinking-mode configuration; see ReasoningConfig.
Sampling temperature between 0 and 2; has no effect in thinking mode.
Shape of the answer, including JSON-Schema-constrained output; see TextConfig.
Which tool, if any, the model must call.
Tools the model may use — functions, and the server-side web search.
How many most likely tokens to report at each position.