MiniMax (official) · @MiniMax_AI · X·2026-07-08 15:57·54天前
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。

MiniMax (official)@MiniMax_AI
51AI 编辑部评分,满分 100
2026-07-08 15:57· 54天前
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。

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. 🤝

Together AIWe're introducing Provisioned Throughput: reserved inference capacity for frontier open models, with token-based pricing and a 99% uptime SLA. Serverless simpli...

来源:MiniMax (official)· x.com