pub struct ResponsesRequest {Show 14 fields
pub client: DeepSeekClient,
pub model: String,
pub input: Option<Input>,
pub instructions: Option<String>,
pub reasoning: Option<Reasoning>,
pub max_output_tokens: Option<u32>,
pub stream: Option<bool>,
pub temperature: Option<f64>,
pub top_p: Option<f64>,
pub text: Option<Text>,
pub tools: Vec<Tool>,
pub tool_choice: Option<ToolChoice>,
pub top_logprobs: Option<u32>,
pub user: Option<String>,
}Expand description
Responses request body for the OpenAI Responses API format.
Fields§
§client: DeepSeekClient§model: StringID of the model to use. The Responses API currently only supports deepseek-v4-flash.
input: Option<Input>The input to the model. Either a plain string (treated as a single user message),
or a list of input items.
At least one of input and instructions is required.
instructions: Option<String>A system-level instruction, inserted as the first system message of the model’s context.
reasoning: Option<Reasoning>Configuration of the thinking mode.
max_output_tokens: Option<u32>An upper bound for the number of tokens that can be generated in the response, including both the visible output tokens and the reasoning tokens.
stream: Option<bool>If set to true, the response is streamed as semantic server-sent events.
The final event is response.completed / response.incomplete / response.failed
(there is no data: [DONE] message).
temperature: Option<f64>Possible values: <= 2
Default value: 1
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. Has no effect in thinking mode.
top_p: Option<f64>Possible values: <= 1
Default value: 1
An alternative to sampling with temperature, called nucleus sampling. Has no effect in thinking mode.
text: Option<Text>Configuration of the text output.
tools: Vec<Tool>A list of tools the model may call. Function names must be non-empty, at most 128 characters,
match ^[a-zA-Z0-9_-]+$, and be unique across all tools.
Besides function, the built-in web_search tool is supported and executed on the server side.
tool_choice: Option<ToolChoice>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 (default) 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", "name": "my_function"} forces the model
to call that tool.
top_logprobs: Option<u32>Possible values: <= 20
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.
user: Option<String>A custom end-user identifier, with allowed character set [a-zA-Z0-9\-_] and a maximum length
of 512. Do not include user privacy information.
Trait Implementations§
Source§impl Clone for ResponsesRequest
impl Clone for ResponsesRequest
Source§fn clone(&self) -> ResponsesRequest
fn clone(&self) -> ResponsesRequest
1.0.0 (const: unstable) · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source. Read more