llm4s-core/org.llm4s/org.llm4s.llmconnect/org.llm4s.llmconnect.provider/CostEstimator

CostEstimator

org.llm4s.llmconnect.provider.CostEstimator

Centralized cost estimation for LLM completions.

This provides a single source of truth for estimating completion costs based on token usage and model pricing information. It integrates with the ModelRegistry to look up pricing data and applies it to usage statistics.

The estimator:

Uses existing ModelPricing logic (no duplication)
Returns None if pricing is unavailable
Preserves precision of micro-cost values
Works uniformly across all providers

Example usage:

 val usage = TokenUsage(promptTokens = 100, completionTokens = 50, totalTokens = 150)
 val cost = CostEstimator.estimate("gpt-4o", usage)
 // cost: Some(0.0015) for gpt-4o pricing

Attributes

Graph
Supertypes: class Object

trait Matchable

class Any
Self type: CostEstimator.type

Members list

Value members

Concrete methods

Estimate the cost of a completion based on model and token usage.

This method looks up the model's pricing information and applies it to the provided usage statistics. It handles:

Standard prompt and completion tokens
Thinking tokens (billed at completion token rate)
Missing pricing data (returns None)

Value parameters

model: The model identifier (e.g., "gpt-4o", "claude-3-7-sonnet-latest")
usage: Token usage statistics from the completion

Attributes

Returns: Estimated cost in USD, or None if pricing is unavailable

Estimate cost using pre-fetched model metadata.

This is useful when the caller already has ModelMetadata (e.g., from a provider implementation that caches metadata lookups).

Value parameters

metadata: Model metadata containing pricing information
usage: Token usage statistics

Attributes

Returns: Estimated cost in USD, or None if pricing is unavailable

In this article

Generated with