Struct Usage | NVIDIA NeMo Relay

Generated from cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-ffi.

pub struct Usage {
    pub prompt_tokens: Option<u64>,
    pub completion_tokens: Option<u64>,
    pub total_tokens: Option<u64>,
    pub cache_read_tokens: Option<u64>,
    pub cache_write_tokens: Option<u64>,
    pub cost: Option<CostEstimate>,
}

Token usage statistics from an LLM API response.

All fields are Option<u64> because not every provider supplies every field. For example, cache token counts are only available from providers that support prompt caching.

Fields

`prompt_tokens: Option<u64>`

Tokens consumed by the prompt/input.

`completion_tokens: Option<u64>`

Tokens generated in the completion/output.

`total_tokens: Option<u64>`

Total tokens (prompt + completion).

`cache_read_tokens: Option<u64>`

Tokens served from prompt cache (read).

`cache_write_tokens: Option<u64>`

Tokens written to prompt cache.

`cost: Option<CostEstimate>`

Optional cost reported by provider data or estimated from Relay pricing.

Trait Implementations

`impl Clone for Usage`

impl Clone for Usage

`clone`

fn clone(&self) -> Usage

`clone_from`

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

`impl Debug for Usage`

impl Debug for Usage

`fmt`

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

`impl Default for Usage`

impl Default for Usage

`default`

fn default() -> Usage

`impl<'de> Deserialize<'de> for Usage`

impl<'de> Deserialize<'de> for Usage

`deserialize`

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
    __D: Deserializer<'de>,

`impl PartialEq for Usage`

impl PartialEq for Usage

`eq`

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

`ne`

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

`impl Serialize for Usage`

impl Serialize for Usage

`serialize`

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

`impl StructuralPartialEq for Usage`

impl StructuralPartialEq for Usage