MiniMax (official)· @MiniMax_AI · X·· 2026-07-08AI 评分51
AI 导读
MiniMax 宣布与 Together Compute 合作，其 M3 开放模型上线 Provisioned Throughput（保留推理容量）服务。该服务提供基于 token 的定价、99% 正常运行时间 SLA，以及无服务器化的容量保证，相比 Opus 4.8 降低高达 90% 成本。同批支持的还有 GLM-5.2 模型。
正文 · 原文
Excited to see this go live with the @togethercompute team.
As more production workloads move to open models, reliable infrastructure becomes just as important as the models themselves.
Proud to see M3 launch with Provisioned Throughput. 🤝
We're introducing Provisioned Throughput: reserved inference capacity for frontier open models, with token-based pricing and a 99% uptime SLA. Serverless simplicity, guaranteed capacity, up to 90% lower cost vs. Opus 4.8. Get started with MiniMax M3 + GLM-5.2, read more 🧵在 X 查看被引用的帖子
来源：MiniMax (official) · x.com