Struct SavingsAssumptions 

pub struct SavingsAssumptions {
    pub price_in_per_mtok: f64,
    pub cache_write_mult: f64,
    pub cache_read_mult: f64,
    pub reread_turns: f64,
}

Assumptions behind estimate_saved_cost. Token reduction is not the same thing as billed-cost reduction (arXiv:2607.12161): with provider prompt caching, a tool-output token is written to the cache once at a write premium and then re-read at a steep discount on every subsequent turn. A saved token therefore avoids one cache write plus N cache reads — not one list-price input token.

Fields

price_in_per_mtok: f64

USD per 1M input tokens at the list price.

cache_write_mult: f64

Cache-write premium over the input price (Anthropic: 1.25).

cache_read_mult: f64

Cache-read discount multiplier (Anthropic: 0.10).

reread_turns: f64

Expected number of subsequent turns that re-read the saved tokens before the session ends or compacts.

Trait Implementations

impl Clone for SavingsAssumptions

fn clone(&self) -> SavingsAssumptions

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SavingsAssumptions

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

Formats the value using the given formatter.

impl Default for SavingsAssumptions

fn default() -> Self

Returns the “default value” for a type.