Struct TokenUsage 

pub struct TokenUsage {
    pub input_tokens: Option<u64>,
    pub output_tokens: Option<u64>,
    pub cached_input_tokens: Option<u64>,
    pub cache_creation_input_tokens: Option<u64>,
}

Fields

input_tokens: Option<u64>

Total prompt size: uncached + cached input tokens (including the cache-write subset when the provider reports it separately).

output_tokens: Option<u64>

cached_input_tokens: Option<u64>

Subset of input_tokens that was served from the model_provider’s prompt cache (Anthropic cache_read_input_tokens, OpenAI prompt_tokens_details.cached_tokens).

cache_creation_input_tokens: Option<u64>

Subset of input_tokens that the model_provider wrote into its prompt cache on this request (Anthropic cache_creation_input_tokens, OpenAI-compatible prompt_tokens_details.cache_creation_input_tokens). Providers bill these at a premium over the plain input rate.

Trait Implementations

impl Clone for TokenUsage

fn clone(&self) -> TokenUsage

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TokenUsage

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

Formats the value using the given formatter.

impl Default for TokenUsage

fn default() -> TokenUsage

Returns the “default value” for a type.