llm4s-core/org.llm4s/org.llm4s.agent/ModelUsage

ModelUsage

org.llm4s.agent.ModelUsage

See theModelUsage companion object

case class ModelUsage(requestCount: Long, inputTokens: Long, outputTokens: Long, thinkingTokens: Long, totalCost: BigDecimal)

Accumulates token and cost statistics for a single model across one or more requests.

totalCost is stored as BigDecimal to avoid floating-point accumulation drift that would occur when summing many Double values; incoming Option[Double] costs are converted once via BigDecimal.decimal on first contact.

Value parameters

inputTokens: cumulative prompt tokens sent to the model
outputTokens: cumulative completion tokens received from the model
requestCount: number of API calls attributed to this model
thinkingTokens: cumulative extended-thinking tokens (Anthropic only; zero for other providers)
totalCost: cumulative estimated cost in USD; BigDecimal(0) when cost data is unavailable

Attributes

Companion: object
Graph
Supertypes: trait Serializable

trait Product

trait Equals

class Object

trait Matchable

class Any
Show all

Members list

Value members

Concrete methods

Returns a new ModelUsage with usage and cost folded in.

Value parameters

cost: optional estimated cost in USD; treated as zero when absent
usage: token-usage record from a org.llm4s.llmconnect.model.Completion

Attributes

Combines two ModelUsage records by summing every field.

Useful when aggregating per-model statistics from parallel agent runs or multi-step pipelines where each step produces its own ModelUsage.

Attributes

Inherited methods

Attributes

Inherited from:: Product

Attributes

Inherited from:: Product

In this article

Generated with