Struct RequestBody 

pub struct RequestBody {

    pub audio: Option<ChatCompletionAudioParam>,
    pub frequency_penalty: Option<f32>,
    pub logprobs: Option<bool>,
    pub max_completion_tokens: Option<u32>,
    pub max_tokens: Option<u32>,
    pub messages: Vec<Message>,
    pub logit_bias: Option<HashMap<u32, i32>>,
    pub moderation: Option<ChatModerationParam>,
    pub metadata: Option<HashMap<String, String>>,
    pub modalities: Option<Vec<Modality>>,
    pub model: String,
    pub n: Option<u32>,
    pub parallel_tool_calls: Option<bool>,
    pub prediction: Option<ChatCompletionPredictionContentParam>,
    pub presence_penalty: Option<f32>,
    pub prompt_cache_key: Option<String>,
    pub prompt_cache_options: Option<PromptCacheOptions>,
    pub reasoning_effort: Option<ReasoningEffort>,
    pub response_format: Option<ResponseFormat>,
    pub safety_identifier: Option<String>,
    pub seed: Option<i64>,
    pub service_tier: Option<ServiceTier>,
    pub stop: Option<StopKeywords>,
    pub store: Option<bool>,
    pub stream: Option<bool>,
    pub stream_options: Option<StreamOptions>,
    pub temperature: Option<f32>,
    pub top_p: Option<f32>,
    pub tool_choice: Option<ToolChoice>,
    pub tools: Option<Vec<RequestTool>>,
    pub top_logprobs: Option<u32>,
    pub thinking: Option<DeepSeekThinking>,
    pub user_id: Option<String>,
    pub enable_thinking: Option<bool>,
    pub thinking_budget: Option<u32>,
    pub top_k: Option<u32>,
    pub user: Option<String>,
    pub verbosity: Option<LowMediumHighEnum>,
    pub web_search_options: Option<WebSearchOptions>,
    pub extra_body_map: Option<Map<String, Value>>,
}

Creates a model response for the given chat conversation.

Example

use futures_util::StreamExt;
use openai_interface::chat::create::request::{Message, RequestBody};
use openai_interface::rest::{default_client, post::PostStream, RequestOptions};

const DEEPSEEK_CHAT_URL: &'static str = "https://api.deepseek.com";
const DEEPSEEK_MODEL: &'static str = "deepseek-v4-flash";

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    // Needs the `ferritls` cargo feature; drop this line if you install
    // your own rustls crypto provider (see `openai_interface::rest`).
    openai_interface::rest::install_crypto_provider().ok();

    let request = RequestBody {
        messages: vec![
            Message::System {
                content: "This is a request of test purpose. Reply briefly".into(),
                name: None,
            },
            Message::User {
                content: "What's your name?".into(),
                name: None,
            },
        ],
        model: DEEPSEEK_MODEL.to_string(),
        stream: Some(true),
        ..Default::default()
    };

    let mut response = request
        .get_stream_response_string(&default_client(), DEEPSEEK_CHAT_URL, &RequestOptions::bearer("YOUR_API_KEY"))
        .await?;

    while let Some(chunk) = response.next().await {
        println!("{}", chunk?);
    }
    Ok(())
}

Fields

audio: Option<ChatCompletionAudioParam>

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.

frequency_penalty: Option<f32>

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.

logprobs: Option<bool>

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

max_completion_tokens: Option<u32>

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

max_tokens: Option<u32>

The maximum number of tokens that can be generated in the chat completion. Deprecated according to OpenAI’s Python SDK in favour of max_completion_tokens.

messages: Vec<Message>

A list of messages comprising the conversation so far.

logit_bias: Option<HashMap<u32, i32>>

Modify the likelihood of specified tokens appearing in the completion.

Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100.

moderation: Option<ChatModerationParam>

Configuration for running moderation on the request input and generated output.

metadata: Option<HashMap<String, String>>

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

modalities: Option<Vec<Modality>>

Output types that you would like the model to generate. Most models are capable of generating text, which is the default:

["text"]

The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:

["text", "audio"]

model: String

Name of the model to use to generate the response.

n: Option<u32>

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

parallel_tool_calls: Option<bool>

Whether to enable parallel function calling during tool use.

prediction: Option<ChatCompletionPredictionContentParam>

Static predicted output content, such as the content of a text file that is being regenerated.

presence_penalty: Option<f32>

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.

prompt_cache_key: Option<String>

Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.

prompt_cache_options: Option<PromptCacheOptions>

Options for prompt caching. Supported for gpt-5.6 and later models. By default, OpenAI automatically chooses one implicit cache breakpoint; set mode to explicit to disable the implicit breakpoint. Learn more.

reasoning_effort: Option<ReasoningEffort>

Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, xhigh, and max (model-dependent). Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Defaults are provider- and model-dependent: e.g. medium for GPT-5.5. Providers map unsupported values to the nearest effort level.

response_format: Option<ResponseFormat>

specifying the format that the model must output.

Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide. Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

safety_identifier: Option<String>

A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user. It is recommended to hash their username or email address, in order to avoid sending any identifying information.

seed: Option<i64>

If specified, the system will make a best effort to sample deterministically. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

service_tier: Option<ServiceTier>

Specifies the processing type used for serving the request.

• If set to ‘auto’, then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use ‘default’.
• If set to ‘default’, then the request will be processed with the standard pricing and performance for the selected model.
• If set to ‘flex’ or ‘priority’, then the request will be processed with the corresponding service tier.
• When not set, the default behavior is ‘auto’.

When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.

stop: Option<StopKeywords>

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

store: Option<bool>

Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

Supports text and image inputs. Note: image inputs over 8MB will be dropped.

stream: Option<bool>

Whether to stream back partial progress. If set to true (or left as Some(true)), tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.

Although it is optional, you should explicitly designate it for an expected response.

stream_options: Option<StreamOptions>

Options for streaming response. Only set this when you set stream: true

temperature: Option<f32>

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. It is generally recommended to alter this or top_p but not both.

top_p: Option<f32>

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

It is generally recommended to alter this or temperature but not both.

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 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", "function": {"name": "my_function"}} forces the model to call that tool.

tools: Option<Vec<RequestTool>>

A list of tools the model may call.

top_logprobs: Option<u32>

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. logprobs must be set to true if this parameter is used.

thinking: Option<DeepSeekThinking>

DeepSeek: controls the switch between thinking and non-thinking mode. Defaults to enabled. See the DeepSeek API reference.

user_id: Option<String>

DeepSeek: a custom user ID. Allowed character set is [a-zA-Z0-9\-_] with a maximum length of 512. Do not include user privacy information. It can be used to distinguish user identities for content safety review, isolate KVCache, and schedule users.

enable_thinking: Option<bool>

Qwen: whether to enable thinking mode for hybrid-thinking models such as Qwen3. When set to true, the thinking content is returned in the reasoning_content field.

thinking_budget: Option<u32>

Qwen: the maximum number of tokens available for the model’s thinking (chain-of-thought) process.

top_k: Option<u32>

Qwen: the size of the candidate set for sampling during generation. Set to null or a value greater than 100 to disable top_k sampling.

user: Option<String>

This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

verbosity: Option<LowMediumHighEnum>

Constrains the verbosity of the model’s response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.

web_search_options: Option<WebSearchOptions>

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.

extra_body_map: Option<Map<String, Value>>

Other request bodies that are not in standard OpenAI API and not covered by the fields above.

Implementations

impl RequestBody

pub fn is_streaming(&self) -> bool

Whether this request asks for a streamed response. Defaults to false when RequestBody::stream is None.

Trait Implementations

impl Clone for RequestBody

fn clone(&self) -> RequestBody

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for RequestBody

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for RequestBody

fn default() -> RequestBody

Returns the “default value” for a type.

impl Post for RequestBody

fn build_url(&self, base_url: &str) -> Result<String, OapiError>

Builds the URL for the request.

base_url should be like https://api.openai.com/v1

fn is_streaming(&self) -> bool

impl PostNoStream for RequestBody

type Response = ChatCompletion

fn get_response_string( &self, client: &Client, base_url: &str, options: &RequestOptions, ) -> impl Future<Output = Result<String, OapiError>> + Send + Sync

Sends a POST request and returns the raw response body.

fn get_response( &self, client: &Client, url: &str, options: &RequestOptions, ) -> impl Future<Output = Result<Self::Response, OapiError>> + Send + Sync

Sends a POST request and deserializes the response.

impl PostStream for RequestBody

type Response = ChatCompletionChunk

fn get_stream_response_string( &self, client: &Client, base_url: &str, options: &RequestOptions, ) -> impl Future<Output = Result<impl Stream<Item = Result<String, OapiError>> + Send + Unpin + 'static, OapiError>> + Send + Sync

Sends a streaming POST request and returns the raw SSE data items as strings.

fn get_stream_response( &self, client: &Client, base_url: &str, options: &RequestOptions, ) -> impl Future<Output = Result<impl Stream<Item = Result<Self::Response, OapiError>> + Send + Unpin + 'static, OapiError>> + Send + Sync

Sends a streaming POST request and deserializes every SSE data item into Self::Response.

impl Serialize for RequestBody

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.