{"slug": "minimax-opens-m3-1-flash-weights-with-together-ai-handling-inference", "title": "MiniMax opens M3.1 Flash weights with Together AI handling inference", "summary": "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.", "body_md": "# MiniMax opens M3.1 Flash weights with Together AI handling inference\n\n**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.**\n\n        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)\n        · Published \n\nPrimary source: [MiniMax](https://x.com/MiniMax_AI/status/2113452026902589732)\n\n## Why it matters\n\nMiniMax 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.\n\n[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.…\n\nWhen 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.", "url": "https://wpnews.pro/news/minimax-opens-m3-1-flash-weights-with-together-ai-handling-inference", "canonical_source": "https://runtimewire.com/article/minimax-m31-flash-open-weights-together-inference", "published_at": "2026-10-23 02:43:11+00:00", "updated_at": "2026-10-23 06:10:08.129730+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-startups", "ai-infrastructure", "ai-tools"], "entities": ["MiniMax", "M3.1 Flash", "Together AI", "Yan Junjie"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/minimax-opens-m3-1-flash-weights-with-together-ai-handling-inference", "markdown": "https://wpnews.pro/news/minimax-opens-m3-1-flash-weights-with-together-ai-handling-inference.md", "text": "https://wpnews.pro/news/minimax-opens-m3-1-flash-weights-with-together-ai-handling-inference.txt", "jsonld": "https://wpnews.pro/news/minimax-opens-m3-1-flash-weights-with-together-ai-handling-inference.jsonld"}}