01Fetches and caches pricing data locally from LiteLLM registry, refreshing every 24 hours
02Estimate cost for a given number of input and output tokens
03Look up pricing, context window, and capabilities for any LLM
04Compare models to find the most cost-effective options based on requirements
05Supports fuzzy matching for model names (e.g., 'sonnet 4.5')
061 GitHub stars