Skip to content
llm-usage-metrics

Pricing

llm-usage-metrics uses LiteLLM pricing data to estimate costs when events do not include explicit cost.

Pricing source

Section titled “Pricing source”
  • primary source: LiteLLM pricing JSON
  • cache: local pricing cache is used when available
  • offline mode: --pricing-offline uses cache only
Terminal window
llm-usage monthly --pricing-offline

If pricing cannot be loaded (or offline cache is unavailable), report generation fails.

For cache lifecycle and tuning knobs, see Caching.

Cost modes

Section titled “Cost modes”

Each event is either:

  • explicit: source included a valid cost
  • estimated: cost derived from pricing data

Explicit costUsd: 0 events are re-priced from LiteLLM when model pricing exists.

Row cost rendering

Section titled “Row cost rendering”
  • - when all contributing events are unresolved
  • ~$... when only part of the row cost is known
  • $... when row cost is fully resolved

Override pricing URL

Section titled “Override pricing URL”
Terminal window
llm-usage monthly --pricing-url https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json