list_models
List LLM models with current pricing in dollars per million tokens. Filter by provider, category, or verified-only.
get_model
Get the full record for one model (input/output/cached price, context window, verification flag, etc).
compare_models
Compare 2-6 models side by side: prices, context window, category, verified flag.
estimate_cost
Estimate dollar cost for a request given a model + token counts. Uses cached_input price when cached_input_tokens > 0.
cheapest_for
Return the 3 cheapest verified models in a given category, ranked by blended (input + output)/2 price.
list_providers
List all providers we track with a count of models and a link to their official pricing page.