Struct CreateMessageRequest 

pub struct CreateMessageRequest {

    pub model: String,
    pub messages: Vec<InputMessage>,
    pub max_tokens: u32,
    pub metadata: Option<Metadata>,
    pub service_tier: Option<ServiceTier>,
    pub stop_sequences: Option<Vec<String>>,
    pub stream: Option<bool>,
    pub system: Option<SystemContent>,
    pub temperature: Option<f64>,
    pub thinking: Option<ThinkingConfig>,
    pub tool_choice: Option<ToolChoice>,
    pub tools: Option<Vec<Tool>>,
    pub top_k: Option<u32>,
    pub top_p: Option<f64>,
    pub container: Option<ContainerConfig>,
    pub mcp_servers: Option<Vec<McpServerConfig>>,
}

Request to create a message using the Anthropic Messages API.

This is the main request type for /v1/messages endpoint.

Fields

model: String

The model that will complete your prompt.

messages: Vec<InputMessage>

Input messages for the conversation.

max_tokens: u32

The maximum number of tokens to generate before stopping.

metadata: Option<Metadata>

An object describing metadata about the request.

service_tier: Option<ServiceTier>

Service tier for the request (auto or standard_only).

stop_sequences: Option<Vec<String>>

Custom text sequences that will cause the model to stop generating.

stream: Option<bool>

Whether to incrementally stream the response using server-sent events.

system: Option<SystemContent>

System prompt for providing context and instructions.

temperature: Option<f64>

Amount of randomness injected into the response (0.0 to 1.0).

thinking: Option<ThinkingConfig>

Configuration for extended thinking.

tool_choice: Option<ToolChoice>

How the model should use the provided tools.

tools: Option<Vec<Tool>>

Definitions of tools that the model may use.

top_k: Option<u32>

Only sample from the top K options for each subsequent token.

top_p: Option<f64>

Use nucleus sampling.

container: Option<ContainerConfig>

Container configuration for code execution (beta).

mcp_servers: Option<Vec<McpServerConfig>>

MCP servers to be utilized in this request (beta).

Implementations

impl CreateMessageRequest

pub fn is_stream(&self) -> bool

Check if the request is for streaming

pub fn get_model(&self) -> &str

Get the model name

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<'de> Deserialize<'de> for CreateMessageRequest

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

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.