API prices for 512K-to-1M context are double the rates at or below 512K
MiniMax's enterprise API pricing page shows that input, cache, and output rates for the 512K-to-1M input range are twice the rates at or below 512K. The current page no longer supports the earlier limited-availability claim.
ActionBudget million-context workloads against the separate tier and regression-test behavior at the 512K boundary.
Verify source