# MiniMax M3 上线 Together Compute Provisioned Throughput

- 来源：MiniMax (official) (@MiniMax_AI)
- 发布时间：2026-07-08 15:57
- AIHOT 分数：51
- AIHOT 链接：https://aihot.virxact.com/items/cmrbt85dc0733ihl1rm82pwjf
- 原文链接：https://x.com/MiniMax_AI/status/2074764808877183255

## AI 摘要

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

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. 🤝

### 引用推文

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