llminfo is in beta, so things may move, break or be briefly wrong. We collect this data automatically from provider APIs, model marketplaces and public leaderboards. We run a data refresh every six hours. Sources can disagree, lag behind or change format, and matching benchmarks to models isn't perfect. Treat it as a starting point, and check prices and terms with the provider before you spend money. A listing isn't an endorsement. Read what researchers found when they tested providers, including resellers serving a cheaper model than the one they advertised.