Struct RuntimeBedrockModel 

pub struct RuntimeBedrockModel { /* private fields */ }

A model selected at runtime, including an exact inference-profile ID or ARN.

Token ceilings are supplied by the caller; this type does not discover account access, service limits, or model capabilities. Constructing it performs no I/O. Unlike some historical typed models, it never opts into global routing.

Implementations

impl RuntimeBedrockModel

pub fn new( name: impl Into<String>, model_id: impl Into<String>, context_tokens: usize, output_tokens: usize, ) -> Result<Self, ProviderError>

Build an owned configuration without leaking strings or selecting a route.

Trait Implementations

impl BedrockModel for RuntimeBedrockModel

fn bedrock_id(&self) -> &str

The Bedrock model ID

fn default_inference_profile(&self) -> InferenceProfile

The default inference profile for this model

impl Clone for RuntimeBedrockModel

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RuntimeBedrockModel

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

Formats the value using the given formatter.

impl Model for RuntimeBedrockModel

fn name(&self) -> &str

Human-readable model name (e.g., “Claude Sonnet 4.5”)

fn max_context_tokens(&self) -> usize

Maximum input context tokens

fn max_output_tokens(&self) -> usize

Maximum output tokens the model can generate

fn estimate_token_count(&self, text: &str) -> usize

Estimate token count for text

fn estimate_message_tokens(&self, messages: &[Message]) -> usize

Estimate tokens for a conversation

fn estimate_content_block_tokens(&self, block: &ContentBlock) -> usize

Estimate tokens for a single content block