Together AI Launches Provisioned Throughput for Frontier Open Models

Together AI·medium signal

Together AI introduced Provisioned Throughput, giving customers reserved inference capacity for frontier open models like MiniMax M3 and GLM-5.2, with token-based pricing, a 99% uptime SLA, and up to 90% lower cost than proprietary APIs. It's a direct play at enterprises wanting predictable, dedicated capacity on open weights. The pricing claim reinforces the broader open-model margin-compression narrative.