# TypeSafe AI's Jev now available on AI Gateway

By Steven Van · 2026-09-16

TypeSafe AI's Jev returns typed Choice, Score and Boolean answers instead of text, via AI SDK 7's evaluate API.

[Vercel](<https://creatorstoolbox.com/tools/vercel>)'s AI Gateway now supports **Jev**, a probabilistic decision model from TypeSafe AI. Instead of generating text token by token, Jev takes a shared state (a string, object, or array) and a set of typed questions, then returns structured answers, Choice, Score, or Boolean, along with probabilities, evaluating all declared questions in one request.

TypeSafe reports Jev was up to **193.6x faster** and **444.6x cheaper** than LLMs on its own workflow evaluations. Example uses include:

- Choosing the next tool or subagent in an agent loop

- Deciding whether to continue, retry, ask the user, or stop

- Scoring urgency or risk before an action

- Verifying model outputs and enforcing guardrails

Jev is available through the AI SDK's experimental evaluate API, which requires AI SDK 7.0.105 or later and is called with the model ID typesafe-ai/jev. It supports Zero Data Retention and No Training per request, and evaluation calls are billed from the model's per-token rates like other AI Gateway models. Full usage details are in the [evaluation documentation](<https://vercel.com/docs/ai-gateway/modalities/evaluation>).

![Vercel](<https://www.google.com/s2/favicons?domain=vercel.com&sz=128>)

Vercel

The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.

[View Vercel →](<https://creatorstoolbox.com/tools/vercel>)

Sources

[Original source](<https://vercel.com/docs/ai-gateway/modalities/evaluation>)

[Read TypeSafe AI's Jev now available on AI Gateway on Creators Toolbox](<https://creatorstoolbox.com/blog/vercel-typesafe-ai-s-jev-now-available-on-ai-gateway>)

---
Canonical source: https://creatorstoolbox.com/blog/vercel-typesafe-ai-s-jev-now-available-on-ai-gateway