MiniMax M3.1 Flash 正式上线 Ollama Cloud，提供美国托管与零数据留存
MiniMax 与 Ollama 合作推出 MiniMax M3.1 Flash 的首发支持，支持 100 万 token 上下文，并在 Ollama Cloud 提供限时免费体验。
MiniMax 正式宣布与开源 AI 运行平台 Ollama 达成合作，为旗下最新的 MiniMax M3.1 Flash 模型提供首发上线（Day-0）支持。开发者即日起可以通过 Ollama 命令行工具在云端直接调用该模型，并支持与 Claude Code 等编程代理工具无缝集成。
根据官方公告，MiniMax M3.1 Flash 部署于美国境内的云基础设施，并严格遵循零数据留存（Zero Data Retention）隐私策略。该模型具备原生多模态图像理解能力与高达 100 万 token 的超长上下文窗口，专为代码编写与自主智能体（Agent）工作流进行了深度优化。
作为上线合作的一部分，Ollama Cloud 面向全体开发者提供为期 3 天的 M3.1 Flash 免费使用权限，旨在降低开发者探索与构建高性能 Agent 架构的门槛。
来源证据
minimax-m3ollama.com · supportingOllama 447.9K Downloads Updated 2 months ago ## MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality. ## Applications Claude Code `ollama launch claude --model minimax-m3:cloud` OpenCode `ollama launch opencode --model minimax-m3:cloud` Hermes Agent `ollama launch hermes --model minimax-m3:cloud` OpenClaw `ollama launch openclaw --model minimax-m3:cloud` ## Models Name 1 model Size / Usage Context Input minimax-m3:cloud High Usage · 512K context window · Text, Image · 2 months ago 512K Text, Image ## Readme Ollama’s Cloud is officially licensed with MiniMax for commercial usage In partnership with MiniMax, the M3 model on Ollama’s Cloud is US-based with zero data retention. ### Highlights
MiniMax M3 and Qwen 3.7 on Ollama: Agent Setup Guidebetterclaw.io · supporting### The cloud path (works right now, 2 minutes) ``` # Install Ollama if you haven't # Install Ollama if you haven't brew install ollama # Mac brew install ollama # Mac # or: curl -fsSL | sh # Linux # or: curl -fsSL | sh # Linux # Pull MiniMax M3 Cloud # Pull MiniMax M3 Cloud ollama pull minimax-m3:cloud ollama pull minimax-m3:cloud # Test it # Test it ollama run minimax-m3:cloud "Write a Python function to parse invoices" ollama run minimax-m3:cloud "Write a Python function to parse invoices" ``` That's it. The `:cloud` tag sends your requests to Ollama's US-hosted infrastructure with zero data retention. In partnership with MiniMax, this instance runs on US servers specifically. For agent integration, point your framework's Ollama endpoint at M3: [...] ### Can I run MiniMax M3 locally on Ollama? Yes, with caveats. Ollama offers M3 as a cloud-hosted model (`minimax-m3:cloud`) that runs on US servers with zero data retention. For fully local deployment, MiniMax released
Ollama's Postlinkedin.com · supportingWith Ollama's Cloud, this model's hosting will be US-based with zero data retention. M3 supports up to 1M tokens. US-based hosting, zero data
MiniMax (official) on X: "Day0 support from @ollama 🦙🤝🐰 M3.1 Flash, US-hosted, zero data retention, ready for your agents. Go build!" / Xx.com · supportingLog inSign up ## Post Log inSign up # MiniMax (official) on X: "Day0 support from @ollama 🦙🤝🐰 M3.1 Flash, US-hosted, zero data retention, ready for your agents. Go build!" @MiniMax_AI MiniMax (official)@MiniMax\_AI Day0 support from @ollama 🦙🤝🐰 M3.1 Flash, US-hosted, zero data retention, ready for your agents. Go build! @ollama ollama@ollama 7h MiniMax M3.1 Flash is on Ollama! 🔒 Hosted in the US and with zero data retention. Fast coding and agentic workflows, with image understanding and a 1M-token context window. Try it on Ollama Cloud: ollama run minimax-m3.1-flash:cloud Claude Code: ollama launch claude --model Quote @MiniMax_AI MiniMax (official) @MiniMax\_AI 14h [...] @MiniMax_AI MiniMax (official) @MiniMax\_AI 14h MiniMax M3.1 Flash: Space Performance + Bunny Speed 🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash. 💰Redefining the performance economics of agentic AI. M3.1 Flash achiev
ollama on X: "MiniMax M3.1 Flash is on Ollama! 🔒 Hosted in the US and with zero data retention. Fast coding and agentic workflows, with image understanding and a 1M-token context window. Try it on Ollama Cloud: ollama run minimax-m3.1-flash:cloud Claude Code: ollama launch claude --model mini… / Xx.com · supportingViews 25 @parthsareen parth ollama @parthsareen 1h so many model drops gotta catch em all @rthiago Thiago@rthiago 2h Von Neumann proved the minimax theorem in 1928: minimize your worst-case loss. Took 98 years, but it finally reached my Claude Code bill. @OneManVibeCode @OneManVibeCode 1h flash models change the budget from tokens to attempts 1 [...] @MiniMax_AI MiniMax (official)@MiniMax\_AI 8h MiniMax M3.1 Flash: Space Performance + Bunny Speed 🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash. 💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence 6:27 PM · Oct 19, 2026·8,157 Views 25 Avatar MiniMax (official)@MiniMax\_AIFollow Code: @MiniMaxAgent MiniMax Design: @Hailuo\_AI API: platform.minimax.io M Plan: minimax.io/m-plan @ollama ollama@ollama [...] Log inSign up ## Post Log inSign up # ollama on X: "MiniMax
ollama on X: "For the next 3 days, in collaboration with @MiniMax_AI, MiniMax M3.1 Flash will be free on Ollama's Cloud! Hosted in the US and with zero data retention." / Xx.com · supportingLog inSign up ## Post Log inSign up # ollama on X: "For the next 3 days, in collaboration with @MiniMax\_AI, MiniMax M3.1 Flash will be free on Ollama's Cloud! Hosted in the US and with zero data retention." @ollama ollama@ollama For the next 3 days, in collaboration with @MiniMax\_AI, MiniMax M3.1 Flash will be free on Ollama's Cloud! Hosted in the US and with zero data retention. @ollama ollama@ollama 8h MiniMax M3.1 Flash is on Ollama! 🔒 Hosted in the US and with zero data retention. Fast coding and agentic workflows, with image understanding and a 1M-token context window. Try it on Ollama Cloud: ollama run minimax-m3.1-flash:cloud Claude Code: ollama launch claude --model 1:41 AM · Oct 20, 2026·7,944 Views 17 Avatar MiniMax (official)@MiniMax\_AIFollow [...] Views 17 Avatar MiniMax (official)@MiniMax\_AIFollow Code: @MiniMaxAgent MiniMax Design: @Hailuo\_AI API: platform.minimax.io M Plan: minimax.io/m-plan @ollama ollama@ollama For the next 3 days, in c