pub struct ModelBillingTokenPrices {
pub batch_size: Option<i64>,
pub cache_price: Option<f64>,
pub cache_read_price: Option<f64>,
pub cache_write_price: Option<f64>,
pub context_max: Option<i64>,
pub input_price: Option<f64>,
pub long_context: Option<ModelBillingTokenPricesLongContext>,
pub max_prompt_tokens: Option<i64>,
pub output_price: Option<f64>,
}Expand description
Re-exports of generated protocol types that are part of the SDK’s
public API surface. The canonical definitions live in
crate::rpc; they live here so the crate-root
pub use types::* surfaces them alongside hand-written SDK types.
Token-level pricing information for this model
Fields§
§batch_size: Option<i64>Number of tokens per standard billing batch
cache_price: Option<f64>Deprecated: use cacheReadPrice. AI Credits cost per billing batch of cached tokens
cache_read_price: Option<f64>AI Credits cost per billing batch of cached (read) tokens
cache_write_price: Option<f64>AI Credits cost per billing batch of cache-write (cache creation) tokens.
context_max: Option<i64>Deprecated: use maxPromptTokens. Prompt token budget for the default tier. The total context window is this value plus the model’s max_output_tokens.
input_price: Option<f64>AI Credits cost per billing batch of input tokens
long_context: Option<ModelBillingTokenPricesLongContext>Long context tier pricing (available for models with extended context windows)
max_prompt_tokens: Option<i64>Prompt token budget for the default tier. The total context window is this value plus the model’s max_output_tokens.
output_price: Option<f64>AI Credits cost per billing batch of output tokens
Trait Implementations§
Source§impl Clone for ModelBillingTokenPrices
impl Clone for ModelBillingTokenPrices
Source§fn clone(&self) -> ModelBillingTokenPrices
fn clone(&self) -> ModelBillingTokenPrices
1.0.0 (const: unstable) · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source. Read more