Models
19 models from 5 providers, on one OpenAI-compatible endpoint.
MiniMax: MiniMax M2.5
FlashfastbudgetFlashEarlier MiniMax generation, still very cheap per token.
eaon/minimax-m2.5200K contextFree, Go, Plus, Pro, MaxMiniMax: MiniMax M2.5 HighSpeed
FlashfastbudgetFlashM2.5 HighSpeed for tight latency budgets.
eaon/minimax-m2.5-highspeed200K contextFree, Go, Plus, Pro, MaxMiniMax: MiniMax M2.7
FlashfastbudgetFlashBalanced M2.7 for general chat and code assist.
eaon/minimax-m2.7200K contextFree, Go, Plus, Pro, MaxMiniMax: MiniMax M2.7 HighSpeed
FlashfastbudgetFlashM2.7 tuned for latency. Same cost as the quality path.
eaon/minimax-m2.7-highspeed200K contextFree, Go, Plus, Pro, MaxMiniMax: MiniMax M3
FlashfastbudgetFlashTop MiniMax line. Cheap long-context agent work.
eaon/minimax-m3200K contextFree, Go, Plus, Pro, Max
Showing 5 of 19 models. Every call bills its real token cost against your plan's usage grant.