Groq · minimax

Cloud PlatformOpenAI compatible

Ultra-fast inference platform powered by custom LPU hardware for low-latency AI.

Active models
12+ 8 deprecated
Families
11
Headquarters🇺🇸 Mountain View, CA
Founded2016
API Base URL
Modelsconsole.groq.com/docs/models
Capabilities
Model
MiniMax M2.7 Enterpriseminimaxai/minimax-m2.7