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.
What happened?
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.”
Why it matters
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.
Who is affected?
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.
What else you should know
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?
The link opens in a new window and leads to the publisher's own site.
Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.
AI-verktyg i artikeln
Topics
Get similar news straight to your inbox
The reader's room
Send in a question or an addition. The newsroom reads everything before it's published and replies when relevant. No AI-generated text – just people.
Sign in to submit a comment or question.
Read the article through your role
- Decide whether this affects strategy over 6–12 months or is just noise.
- Discuss with leadership: do we own the right question or does ownership need to move?
- Ask: what risk are we taking by NOT acting on this this quarter?
Generated angle — not editorial analysis of "Together AI Launches Provisioned Throughput for AI Models"