PulseAugur
EN
LIVE 20:30:54

Together Computer launches Provisioned Throughput for open models

Together Computer has launched Provisioned Throughput, a service offering reserved inference capacity for frontier open models. This new offering aims to provide guaranteed capacity with token-based pricing and a 99% uptime SLA, promising up to 90% cost reduction compared to other services. The service is available with MiniMax M3 and GLM-5.2. AI

IMPACT This service aims to lower costs and ensure reliability for running open-source AI models in production environments.

RANK_REASON This is a product launch for an infrastructure service that supports AI models, rather than a core AI model release or research.

Read on X — MiniMax AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Together Computer launches Provisioned Throughput for open models

COVERAGE [1]

  1. X — MiniMax AI TIER_1 English(EN) · MiniMax_AI ·

    Excited to see this go live with the @togethercompute team.

    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. 🤝