Together AI has launched Provisioned Throughput, a new service offering reserved inference capacity for open-source frontier models. This service features token-based pricing and a 99% uptime Service Level Agreement (SLA). It aims to provide serverless simplicity and guaranteed capacity at a significantly lower cost compared to existing solutions like Opus 4.8, with initial support for models such as MiniMax M3 and GLM-5.2. AI
IMPACT Offers a more cost-effective and reliable way to access frontier open-source models for inference.
RANK_REASON Launch of a new service offering by an AI infrastructure provider.
Read on X — Together (inference / OSS) →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →