Back to all models
minimax
minimaxMiniMax: MiniMax M3
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
minimax/minimax-m3
Context Size
1,048.576K
Input Price
45,000 pts/M
Output Price
180,000 pts/M
Architecture
Text
Image
Video
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerOther
Max Completion512,000 tokens
Provider Context524.288K tokens
ModeratedNo
CreatedMay 31, 2026