跳到正文
Vercel Blog(vercel.com)· Amelia Charles·· 2026-09-18品質評分72

Jev 是 AI Gateway 歷史上最快被採用的模型

Jev is the fastest-adopted model in AI Gateway history

重點導讀

Jev 在 AI Gateway 上的首日採用率突破 GPT‑5.6 兩倍,證明專門化決策模型能迅速進入實際工作流程。

  • 首日採用率:24 小時內已達 13% 的付費團隊使用,超過 GPT‑5.6 兩倍、Fable 5.1 六倍。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

正文 · 原文

Within 24 hours of launching on AI Gateway, Jev from TypeSafe AI reached more than twice as many paid teams as any previous model launch, making it the fastest-adopted model in gateway history.

Jev passed every other comparison model in its first twelve hours and continued to widen its lead for the rest of the day. By hour 24, nearly 13% of paid teams were using it. That's 2x the GPT-5.6 family and more than 6x Fable 5.1's share.

Jev’s launch shows how quickly a specialized model can find a place in production. Its first-day adoption was unmatched among recent launches; the next test is whether that early adoption lasts.

About Jev

Jev was introduced on September 15 as a probabilistic decision model designed to support structured decision-making within software. An application sends it context and a set of questions. Jev evaluates those questions in parallel and returns typed choices, scores, or true-or-false answers, along with probabilities.

Unlike the text produced by a general-purpose language model, Jev’s answers come in a format the code can use directly. Developers can use it to:

  • choose an agent’s next tool or subagent

  • decide whether a workflow should continue, retry, ask the user, or stop

  • score urgency or risk before taking an action

  • verify model outputs, enforce guardrails, or send uncertain cases for human review

In its own workflow evaluations, TypeSafe AI reports that Jev was up to 194 times faster and 445 times cheaper than language models.

See the September AI Gateway Production Index for more model usage data, or try Jev through AI Gateway and build with the AI SDK.

Read more

來源: Vercel Blog (vercel.com)
開啟原文

讀者討論

理性交流 · 即時討論