Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Vercel AI Gateway

Vercel AI Gateway model page hosting Jev as typesafe-ai/jev for AI SDK evaluate calls, with no TypeSafe waitlist.

Libraryproduction
Open source ↗

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

Vercel AI Gateway hosts Jev under the model id typesafe-ai/jev. According to the list summaries, developers can call it through the Vercel AI SDK's evaluate interface without joining TypeSafe's waitlist, using Vercel's billing.

Several projects in this directory use the gateway as an alternative route to Jev. Pricing and limits are on Vercel's model page.

What the decision model decides

TypeQuestionAnswers
OtherJev decisions via the AI SDK evaluate interface(inferred)—

How it works

  1. Get a Vercel AI Gateway key.
  2. Use the AI SDK evaluate interface with typesafe-ai/jev.
  3. Read typed results in your app.

Strengths

  • Access to Jev without the TypeSafe waitlist.
  • Integrates with the Vercel AI SDK.

Caveats

  • Gateway adds its own billing and limits.
  • AI SDK evaluate interface is described as experimental elsewhere.

Getting started

See https://vercel.com/ai-gateway/models/jev

At a glance

Type
Library
Status
production
Language
TypeScript
Runtime
Vercel AI Gateway, AI SDK

Use cases and integrations

How curated lists describe it

Frequently asked questions

What is the model id?

typesafe-ai/jev.

Do I need TypeSafe access?

No, the gateway provides access without the waitlist.

How do I call it?

Through the AI SDK's evaluate interface.

Related projects

  • Ax

    Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.

    PluginproductionTypeScript
  • Effect

    Effect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.

    ProjectproductionTypeScript
  • instructor-php

    PHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.

    ProjectproductionPHP
  • req\_llm

    Elixir library for unified LLM calls across providers, with an evaluate interface that calls Jev via TypeSafe or OpenRouter.

    ProjectproductionElixir
  • synkora-ai

    Self-hosted multi-tenant AI agent platform listed as including optional TypeSafe client tools for classification, scoring and yes/no.

    LibraryproductionPython
  • TanStack AI

    Provider-agnostic TypeScript AI SDK; per list sources, an @tanstack/ai-typesafe adapter exposes Jev decisions through decide().

    ServiceproductionTypeScript