Cloudflare Workers AI Jev

Cloudflare documents model id typesafe/jev for TypeSafe's structured evaluation model on Workers AI.

What it does

Cloudflare documents model id typesafe/jev for TypeSafe's structured evaluation model on Workers AI. Context window is listed as 32,000 tokens. Call pattern from Cloudflare docs: env.AI.run('typesafe/jev', { state, questions }) with noul, choice, and score question shapes. Dollar pricing is not published on the model page; Cloudflare points to dashboard pricing. TypeSafe's public list price elsewhere is $0.042 per million input tokens with output free (typesafe.ai blog Sep 15, 2026). Glue code for gateways, agents, and platforms that should stay typed instead of chatty. Tags in the wild: integrations, sdk, agents. Follow the primary link for the author's latest notes and setup quirks.

More in this orbit

Same category, overlapping tags. Hand-picked neighbors, not a black box.

IntegrationsTypeScript5,253

DemoFeatured

eve

Vercel's agent framework with Jev wired into the experimental evaluate path, so scoring stays typed.

integrationsagentseval

Details Demo

Browser and computer usePython4,799

DemoFeatured

Jev Ultrafast

Jev picks the browser op and DOM target in one shot; a tiny LLM only shows up when something needs typing.

by @gregpr07

browser computer usebrowser-useagents

Details Demo

Agent toolingTypeScript2,735

Featured

fast-jev-compaction

Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dro

agent toolingcompactionagents

Details

IntegrationsTypeScript796

DemoFeatured

ai-cli

Vercel Labs terminal CLI that can point evaluate at Jev instead of another vibes-based judge.

integrationseval

Details Demo