Struct ModelPricing 

pub struct ModelPricing {
    pub input: f64,
    pub output: f64,
    pub cached_input: f64,
    pub cached_write_5m: f64,
    pub cached_write_1h: f64,
    pub reasoning: f64,
    pub batch_discount: f64,
}

Per-model pricing in USD per token.

Fields

input: f64

USD per uncached input token.

output: f64

USD per output token.

cached_input: f64

USD per cached input READ token (cache hit). For Anthropic this is ~10% of input; for OpenAI ~50%. If 0.0, cached reads are billed at the full input rate.

cached_write_5m: f64

USD per cached input WRITE token, 5-minute TTL tier. Anthropic charges ~1.25× input for 5m-ephemeral cache creation. If 0.0, cache writes are billed at the uncached input rate.

cached_write_1h: f64

USD per cached input WRITE token, 1-hour TTL tier. Anthropic charges ~2.0× input for 1h-ephemeral cache creation.

reasoning: f64

USD per reasoning / thinking token. If 0.0, reasoning tokens are billed at the output rate.

batch_discount: f64

Multiplier applied to the final per-call cost when meta.batch == true — e.g. 0.5 for a 50% batch discount. 1.0 (or 0.0 as a sentinel) means no discount.

Implementations

impl ModelPricing

pub fn simple(input: f64, output: f64) -> Self

Simple constructor that assumes no caching, no reasoning, no batch.

Trait Implementations

impl Clone for ModelPricing

fn clone(&self) -> ModelPricing

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelPricing

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ModelPricing

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ModelPricing

fn eq(&self, other: &ModelPricing) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for ModelPricing

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ModelPricing