Module response 

Re-exported normalized LLM response data types and core pricing helpers.

Re-exports

pub use super::model_pricing::CacheReadAccounting;

pub use super::model_pricing::ModelPricing;

pub use super::model_pricing::PricingCatalog;

pub use super::model_pricing::PricingCatalogError;

pub use super::model_pricing::PricingConfig;

pub use super::model_pricing::PricingResolver;

pub use super::model_pricing::PricingSource;

pub use super::model_pricing::PricingSourceConfig;

pub use super::model_pricing::PricingUnit;

pub use super::model_pricing::PromptCachePricing;

pub use super::model_pricing::TokenPricingRates;

pub use super::model_pricing::active_pricing_resolver;

pub use super::model_pricing::attach_estimated_cost;

pub use super::model_pricing::attach_estimated_cost_for_provider;

pub use super::model_pricing::estimate_cost;

pub use super::model_pricing::estimate_cost_for_provider;

pub use super::model_pricing::estimate_cost_with_catalog;

pub use super::model_pricing::estimate_cost_with_provider;

pub use super::model_pricing::infer_model_provider;

pub use super::model_pricing::pricing_for_model;

pub use super::model_pricing::pricing_for_provider;

pub use super::model_pricing::reset_active_pricing_resolver;

pub use super::model_pricing::set_active_pricing_resolver;

Structs

AnnotatedLlmResponse

Structured view of an LLM response, produced by a response codec from raw JSON API output.

CostEstimate

Normalized LLM response cost.

ResponseToolCall

A tool call requested by the model in its response.

Usage

Token usage statistics from an LLM API response.

Enums

ApiSpecificResponse

API-specific response data that cannot be normalized across providers.

CostSource

Source of a normalized cost value.

FinishReason

Normalized reason why the model stopped generating.