Skip to content
JevDirectory.org
CommunityCookbooks & DemosPlaygroundVerified 2026-09-22

OpenRouter Labs: Prompt to questions

An OpenRouter Labs recipe that has Claude rewrite a pasted prompt into Jev questions, then runs Jev on every row while a chat model races the same job, comparing answers, requests, time, cost, and accuracy.

Category
Cookbooks & Demos
Published by
Community
Author
Added
2026-09-22
Tagscommunityopenrouterplaygroundevaluationapi

Highlights

  • Paste one prompt; Claude rewrites it as Jev questions, then Jev runs them on every row of the chosen dataset.
  • Preset row sets are Support, Reviews, and Leads, and running requires signing in to OpenRouter.
  • Jev races the chat model on the same job, started at the same moment, so the comparison is head to head.
  • A live panel tracks answers, requests, time, cost, and accuracy for both sides; before a run it reads 'Nothing compared yet'.
  • The recipe links to the typesafe/jev-1.13 model page and sits in OpenRouter's Jev recipes collection at /labs/jev.

Watch out

Sign-in is required to run it, and the fetched page publishes no benchmark results, dataset sizes, or scoring criteria, so it is a comparison harness rather than evidence about accuracy.

More like this

2GitHub stars
Browser lab where every 2048 move is one Jev Choice over the four directions with no heuristic fallback, surfacing the probability distribution, confidence, latency and token cost live.
Cookbooks & Demos#community#typescript#games
Communityjev-2048
A hosted checker and public API that takes a pasted software idea and returns a Jev verdict with success potential, backed by a task guide and a POST /api/fit endpoint.
Cookbooks & DemosPlayground#community#playground#api
Community
181GitHub stars
A MuJoCo and Franka Panda workbench where Jev chooses the next manipulation step for pick-and-place, stacking, and obstacle-carry tasks, with rule baselines and side-by-side model comparison.
Cookbooks & Demos#community#python#robotics
Communityembodied-jev
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Security decisions that fit Jev

This made me rethink where AI actually fits into security engineering. For purely engineering work, forget about ChatGPT or Claude. TypeSafe AI just released Jev, and I think it’s going to change how we build AI into security workflows. Instead of asking an LLM to “investigate Show more

TypeSafe AI
TypeSafe AI
@typesafeai

we are officially out of stealth! join the frontier and get access to Jev on our website (link on profile)

Reply

A million judged questions

Inferring Jev's internals from 1,000 calls

Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more

Reply

The open System One roundup

Jev 发布没几天,开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型: 1、Laya 421M:原生决策模型,支持 Mac 2、Decider-2B:最像 Jev,基于 Qwen3.5 3、NanoJev 0.6B:专门的 Decision Head 4、Reflex:Qwen3.5 + Direct Logits 5、System-One 4B:专门做概率校准 Show more

小墨同学
小墨同学
@xiaomovps

Jev 刚发布没几天,开源社区就出现了同款🔥 Decider-2B模型,是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别: 1、模型 Jev:闭源 System One Model Decider:Qwen3.5-2B,约 1.9B 参数,Apache 2.0 开源 2、价格

Image
Reply

The launch post

Trading bot, one decision per block