Struct CreateMessageRequest 

#[non_exhaustive]
pub struct CreateMessageRequest {

    pub model: ModelId,
    pub max_tokens: u32,
    pub messages: Vec<MessageInput>,
    pub system: Option<SystemPrompt>,
    pub temperature: Option<f32>,
    pub top_p: Option<f32>,
    pub top_k: Option<u32>,
    pub stop_sequences: Option<Vec<String>>,
    pub tools: Vec<Tool>,
    pub tool_choice: Option<ToolChoice>,
    pub metadata: Option<MessageMetadata>,
    pub service_tier: Option<RequestServiceTier>,
    pub thinking: Option<ThinkingConfig>,
    pub mcp_servers: Vec<McpServerConfig>,
    pub container: Option<String>,
    /* private fields */
}

Request payload for POST /v1/messages.

Construct via CreateMessageRequest::builder.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

model: ModelId

Model to query.

max_tokens: u32

Maximum number of output tokens to generate.

messages: Vec<MessageInput>

Conversation history.

system: Option<SystemPrompt>

Optional system prompt.

temperature: Option<f32>

Sampling temperature.

top_p: Option<f32>

Nucleus sampling cutoff.

top_k: Option<u32>

Top-k sampling cutoff.

stop_sequences: Option<Vec<String>>

Custom stop sequences.

tools: Vec<Tool>

Tools the model may invoke.

tool_choice: Option<ToolChoice>

Tool-use policy.

metadata: Option<MessageMetadata>

Optional per-request metadata (user_id).

service_tier: Option<RequestServiceTier>

Request-side service tier preference.

thinking: Option<ThinkingConfig>

Extended-thinking configuration.

mcp_servers: Vec<McpServerConfig>

MCP servers exposed to the model on this request.

container: Option<String>

Container ID for the code-execution built-in tool.

Implementations

impl CreateMessageRequest

pub fn builder() -> CreateMessageRequestBuilder

Begin configuring a request.

Trait Implementations

impl Clone for CreateMessageRequest

fn clone(&self) -> CreateMessageRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CreateMessageRequest

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

Formats the value using the given formatter.

impl From<&CreateMessageRequest> for CountTokensRequest

fn from(req: &CreateMessageRequest) -> Self

Project a CreateMessageRequest onto the subset of fields the count-tokens endpoint accepts. Sampling parameters (temperature, top_p, etc.) and max_tokens are dropped because they don’t affect tokenization.

impl Serialize for CreateMessageRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.