Skip to content
OpenAI· LaunchAvailable

OpenAI opens Decisions API to all – cuts latency to under 200ms

OpenAI has released its Decisions API to all users. The model reduces response times to under 200 milliseconds, enabling faster classification tasks.

By the Aheadline editorial team·24 okt. 2026·2 min read·Source: Entity-watch: OpenAIVerifierad signalAI-generated
OpenAI opens Decisions API to all – cuts latency to under 200ms
OpenAI opens Decisions API to all – cuts latency to under 200ms
By · Verktygs- & infrastrukturreporter
Last updated
Vad betyder det för mig?

What happened?

OpenAI has opened its Decisions API to all customers following its unveiling at the company's developer event on 29 September 2026. The model is a customised version of ChatGPT Luna that processes voice and image alongside text, reducing response times to between 100 and 180 milliseconds. The API functions as a rapid classifier, evaluating predefined options and returning confidence scores at a fraction of the cost of general-purpose language models.

Key facts

Lanseringsdatum22 oktober 2026
Svarstid100–180 millisekunder
Konkurrentens värdering (TypeSafe)7,6 miljarder dollar
BasmodellChatGPT Luna

Why it matters

Historically, large language models have exhibited response times of one to three seconds, creating a bottleneck for interactive voice interfaces and autonomous agents. By focusing the model on discrete choices and rapid decision-making, developers can build significantly more responsive applications at a lower cost per request.

Who is affected?

The launch is aimed at software developers and organisations building autonomous agents or real-time systems where sub-200 millisecond response times are critical. Companies previously forced to rely on expensive and slow language models for simple routing and classification tasks can now substitute them with this specialised API.

Impact on the EU

The Decisions API is available globally to all developers via OpenAI's standard infrastructure, allowing European developers to connect to the interface directly. No specific regulatory hurdles regarding the launch within the EU have been communicated.

What else you should know

By routing inference resources geographically, OpenAI has successfully limited regional latency. The launch puts direct pressure on the startup TypeSafe, which recently reached a valuation of 7.6 billion dollars with its specialised Jev model.

Frequently asked questions

Quick answers about this story

Vad har hänt?
OpenAI har lanserat sitt Decisions API brett till alla kunder, en modell för snabba klassificeringar med svarstider under 200 millisekunder samt stöd för röst och bild.
När hände det?
OpenAI öppnade Decisions API för samtliga kunder den 22 oktober 2026.
Varför spelar det roll?
Det gör det möjligt att bygga realtidssystem och AI-agenter utan de fördröjningar på 1–3 sekunder och höga kostnader som vanliga språkmodeller kräver vid enkla val.
Påverkar det EU?
Ja, API:et är tillgängligt globalt och har geografiskt styrda inferensresurser för att minimera regional fördröjning.
Original source
Entity-watch: OpenAI·siliconreport.com

The link opens in a new window and leads to the publisher's own site.

Verifierad signal

Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.

AI-verktyg i artikeln

Topics

#Voice#OpenAI#API#ChatGPT
[ STAY UP TO DATE ]

Get similar news straight to your inbox

No affiliate linksCancel anytimeGDPR-friendly
[ Frequency ]
[ What do you want to read about? ]

You'll receive updates on 2 topics.

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.

Loading comments…
How this affects you

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 "OpenAI opens Decisions API to all – cuts latency to under 20"