MiniMax opens M3.1 Flash weights with Together AI handling inference

MiniMax, the company led by Yan Junjie, opened the weights for its M3.1 Flash model on October 23rd, four days after launching M3.1 Flash on October 19th, and paired the release with hosted production inference through Together AI. The move lets developers download the weights or run M3.1 Flash through Together AI's hosted service instead of managing their own GPUs.

MiniMax opens M3.1 Flash weights with Together AI handling inference Yan Junjie's company launched M3.1 Flash on October 19th; four days later, it opened the weights and added hosted production inference through Together AI. By Ryan Merket https://runtimewire.com/author/ryan-merket · Published Primary source: MiniMax https://x.com/MiniMax AI/status/2113452026902589732 Why it matters MiniMax is extending M3.1 Flash beyond its own API: downloadable weights widen developer access, while Together AI's hosted inference offers a production route without customer-managed GPUs. MiniMax https://platform.minimax.io/?ref=runtimewire opened the weights for M3.1 Flash on October 23rd https://x.com/MiniMax AI/status/2113452026902589732?ref=runtimewire , pairing the release with production inference through Together AI https://www.together.ai/models/minimax-m3-1-flash?ref=runtimewire so developers can use a hosted service instead of managing GPUs themselves.… When you purchase through links in our articles, we may earn a small commission https://runtimewire.com/affiliate-monetization-standards . This doesn’t affect our editorial independence.