by Minimax
MiniMax-M1 is an open-source large-scale hybrid attention model with 456B total parameters (45.9B activated per token). It natively supports 1M-token context and reduces FLOPs by 75% versus DeepSeek R1 in 100K-token generation tasks via lightning attention. Built on MoE architecture and optimized by CISPO algorithm, it achieves state-of-the-art performance in long-context reasoning and real-world software engineering scenarios.
MiniMax-M1 is an open-source large-scale hybrid attention model with 456B total parameters (45.9B activated per token). It natively supports 1M-token context and reduces FLOPs by 75% versus DeepSeek R1 in 100K-token generation tasks via lightning attention. Built on MoE architecture and optimized by CISPO algorithm, it achieves state-of-the-art performance in long-context reasoning and real-world software engineering scenarios.
On AIHubMix, MiniMaxAI/MiniMax-M1-80k costs $0.6 per million input tokens and $2.4 per million output tokens.
MiniMaxAI/MiniMax-M1-80k is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to MiniMaxAI/MiniMax-M1-80k — no other code changes needed.
MiniMaxAI/MiniMax-M1-80k is developed by Minimax. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
MiniMax H3 is an open, general-purpose multimodal video model provided by MiniMax that…
The MiniMax M3 is a flagship programming model built for real-world productivity. As a…
coding-minimax-m3-free is a free and open version offered by AIHubMix specifically for…
coding-minimax-m2.7-free is a free and open version offered by AIHubMix specifically for…
MiniMax M2.7 can autonomously build complex Agent Harnesses and, leveraging capabilities…
coding-minimax-m2.5-free is a free and open version offered by AIHubMix specifically for…
Use MiniMaxAI/MiniMax-M1-80k via the AIHubMix unified API — one interface for every major LLM.