Playground
CommunityJev Demos & Experiments
Jev AI Playground
A third-party playground and API host for Jev: acceptance-style decision runs with readymade use-case templates, a model menu spanning Jev, Clef, Laya, and others, and 20 welcome credits to try it.
- Format
- Playground
- Reading time
- 2 min
- Published by
- Community
- Last verified
- Oct 2026
- Platforms
- API
- Capabilities
- Requires API key
Highlights
- Runs Jev 1.14 and jev-latest alongside Clef, Clef Flash, Clef-Omni, GPT-6 Luna, Jev-Omni, Laya, and Mercury Decide.
- Templates cover ticket triage, invoice OCR, intent routing, screening, moderation, review scoring, guardrails, and lead qualification.
- Accepts text or JSON plus up to 4 images at 256–1568 pixels per side; images are read for the run only and not saved.
- Starts with 20 welcome credits; a run costs 1 credit or actual input tokens × 1, and output tokens are free.
- Answers come back with Yes/No, Choice, and Score primitives in about half a second.
Watch out
Copy reviewed against the site's fetched text on 2026-10-15. It is a third-party playground, not a TypeSafe property; the site is client-rendered so the capture is text-based, and credits, model menu, and pricing are as displayed on that date.
Questions about this entry
Short answers drawn from the linked project or page.
No. It is a third-party playground and API host at jev-ai.pro that offers the Jev model among several others. Its model menu mixes TypeSafe models with Cloudflare Clef variants, OpenAI's GPT-6 Luna, Laya, and Mercury Decide.
Readymade use-case templates including support ticket triage, invoice OCR, chatbot intent routing, candidate screening, content moderation, product review scoring, LLM guardrails, and sales lead qualification, plus a free-form option for your own case.
The site advertises 20 welcome credits. Each run costs 1 credit, or actual input tokens × 1 when credits are insufficient; output tokens are billed at zero, and there was a 50 percent off promotion displayed on the pricing link.
The model menu lists Jev 1.14 as the recommended text, structured-input, and up-to-4-images option, plus jev-latest as the stable moving alias that the site labels as still pointing at TypeSafe's 1.13.0.
Yes, up to 4 images per run in PNG or JPEG at up to 16 MiB each and 256–1568 pixels per side. Each file gets a key that you write where Jev should look, and images are read for that run only and are not saved.
The same primitives as Jev itself: Yes/No questions with probabilities, Choice questions with per-option probabilities, and Score questions against ordered levels, returned in about half a second per the site's claims.
The site asks you to sign in and provides both a playground and an API surface. The linked API section documents the same model menu for programmatic runs, so treating it as a keyed third-party service rather than an open endpoint is right.
More Jev resources like this
A Beam-hosted playground for comparing open-source alternatives to Jev and running any of them as an API. You edit a state and typed questions in the browser, then call the same model through an OpenAI-compatible endpoint with a workspace token.
Jev Demos & ExperimentsPlayground#community#catalog-import#madewithjev
Community
A public operator lab for TypeSafe Jev: a chess match as the flagship page, a row of smaller judgment booths, and one shared client that keeps the API key out of the browser via a local Python server or a Cloudflare Worker.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
4anti/jev-broadcast-labJavaScript
4anti/jev-broadcast-labJavaScriptA live, graphical dojo for Jev with six real-time canvas scenes over one WebSocket: task routing across model tiers, ticket triage, inbox-scale queues and an honest Jev-vs-Claude gauntlet. Boots in SIM mode without an API key.
Jev Demos & Experiments#community#catalog-import#madewithjev
An independent lab for trying the Jev model: a customer-message example plus experiments for task routing, context selection and evidence checks. It shows choice, score and boolean answers with probabilities and can export the request as TypeScript.
Jev Demos & ExperimentsPlayground#community#catalog-import#yibie
Community
Vercel Labs example that routes three forms by context with Jev and AI SDK: Jev's team choice is accepted when its confidence is at least 95%, otherwise openai/gpt-6-luna-fast independently evaluates the submission and its choice becomes final.
Jev Demos & Experiments#community#catalog-import#logicrw
An interactive experiment for model routing: build a pool of OpenRouter models, hand Jev a task, and watch it pick a model with a full probability distribution — then compare that pick with the answer you judge best and export the record as JSON.
Jev Demos & ExperimentsPlayground#community#catalog-import#logicrw
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.