Struct ModelPricing 

pub struct ModelPricing {
    pub input_per_million: f64,
    pub output_per_million: f64,
    pub cache_read_multiplier: f64,
    pub cache_write_multiplier: f64,
    pub long_prompt: Option<LongPromptRates>,
}

Per-model pricing rates in USD per million tokens, plus the two cache multipliers that turn a raw token count into a billed one.

Cache economics are per-provider, not universal: Anthropic reads at 0.10× and charges a premium to write at 1.25×, OpenAI reads at 0.50× and does not bill writes separately, Gemini reads at 0.25×. A single flat discount mispriced all three, so the rates travel with the model.

Fields

input_per_million: f64

USD per 1 million input (prompt) tokens

output_per_million: f64

USD per 1 million output (completion) tokens

cache_read_multiplier: f64

Fraction of input_per_million at which cache-read tokens bill.

cache_write_multiplier: f64

Fraction of input_per_million at which cache-write tokens bill.

long_prompt: Option<LongPromptRates>

A second rate card for long prompts, when the model has one: a request whose gross prompt exceeds its threshold bills every token — input, cache and output — at the long-prompt rates.

Implementations

impl ModelPricing

pub const fn new(input_per_million: f64, output_per_million: f64) -> Self

Rates for a model that uses the default cache multipliers.

pub const fn with_long_prompt_rates( self, above_prompt_tokens: i64, input_per_million: f64, output_per_million: f64, ) -> Self

Bill a request whose gross prompt exceeds above_prompt_tokens at the given input / output rates instead of the base card.

pub fn rates_for_prompt(&self, prompt_tokens: i64) -> (f64, f64)

The (input, output) rates per million tokens for a request with a gross prompt of prompt_tokens: the long-prompt card above its threshold, the base card otherwise.

pub const fn with_cache_rates(self, read: f64, write: f64) -> Self

Override the cache read/write multipliers for a provider that prices them differently — Anthropic at (0.10, 1.25), OpenAI at (0.50, 1.0).

Trait Implementations

impl Clone for ModelPricing

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for ModelPricing

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 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.