OpenAI opens the Decisions API to all customers, with response times in some scenarios shortened to 100 milliseconds

OpenAI equips GPT-6 with a "fast brain"! Makes decisions in 100 milliseconds, API fully open to all. ZhiDongXi download client. Exclusive first look. October 23, 2026, 16:21:34, from Beijing

ZhiDongXi, October 23 news: according to a TechCrunch report yesterday, OpenAI has opened its Decisions API to all customers. The interface is optimized for inference speed and cost based on the reasoning model GPT-6 Luna, and in some scenarios response time can be shortened from 1 to 3 seconds to 100 to 180 milliseconds.

The Decisions API is mainly aimed at tasks with a clear range of answers. Developers can predefine questions and optional answers, and the model outputs probabilities, options, or scores, for use in content classification, request routing, and deciding what action an AI agent should take next.

On September 15, the AI startup TypeSafe launched the Jev decision model, which can quickly make judgments based on preset options and give confidence levels, helping developers complete classification and task routing at lower cost and faster speed.

OpenAI's opening of the Decisions API this time also means competition in the AI decision model field is further heating up.

1. OpenAI uses existing models to speed up and enter the fast decision market

OpenAI's API product lead Nikunj Handa said that after the team saw the Jev model, it realized this type of decision model has a large number of potential application scenarios.

The team then decided to adjust the inference approach based on the existing foundation reasoning model GPT-6 Luna to shorten response time and reduce cost, rather than training a dedicated decision model from scratch.

Handa said the most notable improvement of the Decisions API is speed, with response time for some tasks shortened from 1 to 3 seconds to 100 milliseconds, 120 milliseconds, or 180 milliseconds.

On September 29, OpenAI announced the Decisions API at its Developer Day event.

▲OpenAI announced the Decisions API at its September 29 Developer Day event. Image source: OpenAI.

On October 6, the interface opened public testing. In a video introducing the Decisions API, Handa also mentioned that in the future OpenAI may conduct dedicated training for this type of task to further improve the model's performance, while currently it mainly achieves the relevant capabilities by adjusting the existing Luna model.

▲OpenAI opened public testing of the Decisions API on October 6. Image source: OpenAI.

On October 22, OpenAI announced the official opening of the interface to all customers. The Decisions API supports receiving text, images, and structured data, and can process up to 400 questions per request, twice the limit during the public testing phase.

▲OpenAI announced on October 22 that the Decisions API is officially open to all customers. Image source: OpenAI.

Enterprises such as the enterprise document management platform Box, the cloud monitoring platform Datadog, the fintech company Ramp, and the language learning platform Speak have used the Decisions API to replace some large model calls to improve task processing speed.

The cloud monitoring and security platform Datadog uses the Decisions API to assess the risk of commands generated by AI agents, with P95 latency about 40 times faster than available frontier models, meaning 95% of requests can complete a response within that time, and only 5% of requests take longer.

The enterprise financial management platform Ramp attributes AI call costs to specific work tasks, improving processing speed by 4 times and reducing costs by 30%.

The language learning platform Speak shortened the waiting time between user actions in GPT-Live from 1.4 seconds to 0.13 seconds, a reduction of more than 90%.

▲OpenAI shows application cases of the Decisions API in enterprises such as Datadog, Ramp, and Speak. Image source: OpenAI.

Among them, the enterprise document management platform Box showed on its official website its process of using the interface to classify business documents and assign them to corresponding processing stages.

▲Box shows the application of the Decisions API in an insurance certificate review process. Image source: Box official blog

2. Two decision models compete on the same stage, third-party evaluation rankings differ

OpenAI's launch of the Decisions API puts it in competition with TypeSafe AI's Jev model. Both products are aimed at software automation tasks and can quickly output decision results based on preset options.

TypeSafe AI was founded in 2024 and mainly develops decision models for software automation. Its co-founder and CEO Diogo Almeida was previously a researcher at OpenAI and participated in related development to improve language models' instruction-following capabilities.

▲Photo of the TypeSafe AI co-founder team. Image source: TypeSafe

On September 15, TypeSafe released its first System One model, Jev. The model can directly output preset options and their corresponding probabilities for software to call. Internal test results published by TypeSafe show that Jev achieved 68% accuracy in 8 workflow tests, tying for 3rd place with OpenAI's Tera model.

▲Ranking of Jev model decision capabilities. Image source: TypeSafe

On October 14, TypeSafe released Jev version 1.14.0, adding features such as image input and updating the model's capabilities. But Almeida mentioned that benchmark results should be treated with caution and suggested developers evaluate model performance in combination with their own workflows.

Third-party leaderboard rankings show different results.

In the System One Index leaderboard released by AIMultiple, the latest Jev model ranks 7th, and OpenAI's Decisions API ranks 14th. The leaderboard comprehensively evaluates model performance across different tasks and calculates a composite index based on scores from various tests.

▲System One Index decision model rankings, image source: AIMultipl

In the Decision Index leaderboard released by Artificial Analysis, the Jev model ranks 2nd, and OpenAI's Decisions API ranks 11th. The leaderboard mainly evaluates model performance from four aspects: knowledge and hallucination control, reasoning, tool calling, and classification.

In addition to test scores, OpenRouter's model usage leaderboard provides another reference: TypeSafe's product remains in a leading position on that leaderboard.

▲OpenRouter model usage leaderboard, image source: OpenRouter

In addition to comparing composite rankings on public leaderboards, there are also tests that examine decision models' continuous judgment ability through actual games.

AI infrastructure company Opper AI developed the JevMan benchmark, having decision models such as Jev play the classic game Pac-Man in real time to observe whether the models can continuously make judgments based on the game situation.

The benchmark has each model play 100 matches against the ghosts in the game and ranks them by average score, while also recording survival time, response latency, fallback action ratio, and per-match cost.

Opper AI Chief Growth Officer Felix Wunderlich said Pac-Man is suitable for testing decision models because the model must decide the next direction within a few hundred milliseconds at every intersection.

▲The JevMan benchmark evaluates decision models' continuous decision-making ability through the Pac-Man game, image source: Opper AI

According to Opper AI's JevMan leaderboard, Jev 1.14 has an average score of 3597 points, ranking 1st; OpenAI's GPT-6 Luna has an average score of 2568 points, ranking 8th.

▲JevMan benchmark model average score leaderboard, image source: Opper AI

Speaking about future development, Handa believes that OpenAI models may have advantages in multimodal capabilities, especially in image classification tasks, where Luna demonstrates strong capability and confidence calibration. He also said that OpenAI customers hope the Decisions API can more flexibly use images as output in the future.

Handa also mentioned that faster response speeds may expand application scenarios for more decision interfaces. If interface response time can be further shortened to about 60 milliseconds, developers may be able to call the interface on every frame of a video to make judgments in real time.

As decision models' response speeds increase and usage costs decrease, developers are expected to apply them to more scenarios that were previously difficult to realize due to excessive latency or cost.

However, whether decision models can play a role in more business scenarios still depends on their accuracy, confidence calibration, and cost performance.

As OpenAI enters this market, developers will have more choices, and actual application results will also become an important criterion for testing the competitiveness of different models.

Source: TechCrunch

"Special statement: The above content (including videos, pictures, or audio if any) is uploaded and published by users of "Dafeng Hao," a self-media platform under Phoenix Net. This platform only provides information storage space services.

Notice: The content above (including the videos, pictures and audios if any) is uploaded and posted by the user of Dafeng Hao, which is a social media platform and merely provides information storage space services."