MiniMax M3.1

The MiniMax M3.1 family from MiniMax introduces native multimodal Mixture-of-Experts model designed for coding, agentic workflows, computer use, and cybersecurity. It brings sparse attention throughout, quantization-aware training, and speculative decoding to million-token text, image, and video workloads.

1 variant

MiniMax M3.1 Flash

MiniMax

Params: 428B

MiniMax M3.1 Flash is a native multimodal Mixture-of-Experts model for coding, agentic workflows, computer use, and cybersecurity across text, image, and video. Its approximately 428B parameters, 23B of them active per token, are arranged in a 60-layer architecture with 6,144 hidden size, 64 attention heads, and 4 KV heads. MiniMax Sparse Attention runs in every layer, while the MoE blocks route each token to 4 of 128 experts plus a shared expert. Supporting a 1M-token context, it combines quantization-aware training with a DSpark draft head for speculative decoding.

Text GenerationInstruction Following+8

Runs onB200+

Runs on

MiniMax M3.1 Models | Vultr Docs