Together AI Launches Provisioned Throughput for AI Models
Together AI introduces "Provisioned Throughput", a service for guaranteed inference capacity for open AI models, aiming to offer cost-efficiency and predictable performance.
Vad har hänt
Together AI has launched a new service called Provisioned Throughput. The service aims to deliver reserved inference capacity for leading open models, such as MiniMax M3 and GLM-5.2. The goal is to simplify the use of advanced AI models for developers.
Key facts
| Tjänstens namn | Provisioned Throughput |
|---|---|
| Lanseringsdatum | 21 maj 2024 |
| Drifttidsgaranti (SLA) | 99% |
| Potentiell kostnadssänkning | Upp till 90% |
”Provisioned Throughput gives you reserved inference capacity for frontier open models like MiniMax M3 and GLM-5.2. Token-based pricing, a 99% uptime SLA, and up to 90% lower cost than proprietary APIs. No GPU-hour math, no infrastructure to manage.”
Varför det spelar roll
This launch addresses the market need for stable and predictable performance when using large language models, particularly for developers who wish to avoid the complexity of GPU management and infrastructure. The service offers token-based pricing and a guaranteed uptime of 99%. Having a dedicated allocation of resources can facilitate development and reduce operating costs.
Vem påverkas
The service is primarily aimed at developers and companies that use or plan to implement open AI models in their applications. Users who want to reduce costs and complexity for inference will be impacted. Specifically, entities currently managing their own GPU infrastructure may see benefits with the new model.
EU-status
Ej relevant för EU-status.
Mer att veta
Together AI highlights that the service can offer up to 90% lower costs compared to proprietary APIs by eliminating the need to manage GPU hours and infrastructure. This underscores a trend towards more optimised cloud services for AI.
Quick answers about this story
Vad har hänt?
När hände det?
Varför spelar det roll?
Vilka modeller stöds?
Länken öppnar i nytt fönster och leder till utgivarens egen sida.
Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.