0.975Claim verification · $0.02 cost per 1,000 cases · 12 of 12 legalbench rank
ArticleBenchmarks and evals
An independent evaluation of Jev, by Vals AI
Ties frontier models on claim verification, last of twelve on LegalBench.
Vals AI
Updated Nov 10, 2026
The newest builds with Jev
855 projects, posts and guides about Jev, the System One model from TypeSafe AI. Each entry links to its source and shows the cost and speed its author reported.
- 855builds
- 181guides
- 21use cases
Diogo Almeida
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
Newest first, 133–165 of 1072. All 1072 in curated order
35,812Jev calls logged · USD 3.68 jev total cost · 44% untrained laya · 94% jev
ArticleBenchmarks and evals
Laya in shadow, next to Jev on every request
Kitsuno trains an open model to replace Jev in production.
Kitsuno
Luis Catacora
@lucataco
Cloudflare's new decision model can see 👀 clef-flash running locally on my M5 Max weights are Apache 2.0. go wild!
XOpen source
clef-flash running locally on an M5 Max
Our guidemadewithjev.com
Jev and MCP
The MCP servers that put Jev inside Claude Code, Cursor and Codex, so an agent can ask for a typed judgment as a tool call. Each one linked, with what it exposes.
Jon Kraayenbrink
@kraayenJon
Jev + LinkedIn bookmarks = your saved posts are finally searchable ✅ 479 posts classified in 225 seconds for $0.0195 🤯 LinkedIn has no native way to search what you saved Jev reads every post and tags the topic, hook, and format you can finally find that post you saved 6 months ago So: save, classify, search. Never lose a good post again. Free and open source. try it below ↓
Peter Steinberger
@steipete
"Today, we’re releasing two Cloudflare-trained decision models, Clef and Clef-flash" blog.cloudflare.com/clef-decision-… Never seen an idea spreading so fast.
Victor M
@victormustar
Alert: Cloudflare just dropped a Jev alternative on Hugging Face 🚨 (Apache 2.0) huggingface.co/Cloudflare/clef
unicode
@unicodef1wn
Guidex.com
AI Company-in-a-Box: Grok Bot + Jev
unicode’s 12-step roadmap for a self-managing company: the Grok Bot marketplace supplies the workers, and Jev answers the five forks between them — who goes next, is the research good enough, continue or stop, is it done, does this need a person.
NO1ennn
@N01ennn
this is pure f*cking treasure A Stanford AI research group finally drew the perfect RAG system: retrieval, Jev and agents in one loop, and it fixes the 3 things that break every RAG app: > the LLM reads 20 passages when only 3 matter > it answers questions your docs can't answer > it trusts whatever text it retrieves here's how it runs: > a lead agent sends the query > hybrid search pulls the top 20 candidates, dense + keyword > ONE Jev request scores all 20 + 2 gates: answerable? injection? > only passages above 0.6 reach the writer agent > a second Jev call checks every claim against its source > grounded answer, with citations and when the docs don't have it: > answerable fails, the writer never runs > a researcher agent rewrites the query and retries once > still nothing? "not in the docs". zero tokens spent on a guess retrieval casts the net. Jev decides what's real. agents do the work save this before you build your next RAG
Gipp 🦅
@gippp69
Jev builders: the model bill is decided before the model is called /routing 20,000 events/day become: → 14,000 die as noise → 4,700 become logs → 800 earn a draft → 500 go to human review only 4% reaches writing. Jev costs $0.84; the full loop lands at $29.04. optimize the 4% before the writer.
XRouting and model choice
20,000 events a day, 4% reach the writer
- Events per day
- 20,000
- Reach the writer
- 4%
- Jev cost
- $0.84
- Full loop
- $29.04
laxman
@llmluthor
Releasing Your Own Jev Post-train a 4B/8B/27B judge on your agent's traces. It beats Jev. 79.7% agreement with human labels vs Jev's 66.3% Beats DeepSeek-V4.1-Flash (763B) by 14 points 0.13s per step on a single GPU Completely open source: recipe, data, training, evals
XOpen source
Post-train your own judge on your agent's traces
- Agreement with humans
- 79.7%
- Jev agreement
- 66.3%
- Per step
- 0.13s
Our guidemadewithjev.com
Jev agent prompts
Copy-paste Jev prompts for coding agents: route models with Jev Router, find wasted tokens, gate tool calls and budgets, and check drafts before they ship. Setup for Claude Code, Cursor, Codex and more.
OpenRouter
@OpenRouter
Introducing typesafe/jev-router: a cache-aware model router powered by Jev and @typesafeai The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. Here's how it works 👇🏻
XRouting and model choice
Jev Router on OpenRouter
Live siteOpen source
Julia 1
A 144.3M-parameter decision model that edges Jev on typed decisions.
Supersonic Labs
144.3M
Live siteOpen source
OpenJev (open weights)
Typed decisions about text, web pages and screenshots, within 2 points of Jev.
OpenJev
84.0% (Jev 85.4%)
Hassan
@nutlope
Guidex.com
How to train your own Jev for $17
Together AI fine-tunes a Jev-like classifier on Qwen3.5 4B: about 38,000 questions sampled from eight public datasets, roughly 25 minutes of training, and the tev1 repository that runs it. The $17 is the training job, not the system around it.
Live siteOpen source
decider-2b
An open reproduction of the System One model class on Qwen3.5-2B.
Mapika
0.577 (v10 0.459)
Our guidemadewithjev.com
Jev agentic harness
An agentic harness where the model proposes and Jev decides, with a receipt per step: 6 published builds, a batched router on a latency deadline, and the rule check that runs in 348 ms.
Live siteOpen source
AgentJev-0.6B
State in. A distribution out. Nothing decoded.
malevrigns
57.8% (606/1048)
Live siteOpen source
APUS-OpenJev-v1
Decision models for browser agents with a selectable compute depth.
APUS AI Lab
85.0% (Jev API 82.5%)
GREG ISENBERG
@gregisenberg
Jev is HERE and this is the CLEAREST explanation of what it is and what NEW businesses it unlocks. (and at the end I'll tell you how to get Jev even if you're on the waitlist) WHAT IT IS You know how you open your inbox and have to decide what's junk, what needs a reply, and what can wait? Jev does that part. It looks at each thing and says "this is junk, I'm 94% sure." It doesn't write anything back to you. It just sorts. 1,700 emails for 18 cents, instantly. That sounds kinda trivial but the important part WHAT IT UNLOCKS My explanation of Jev sounds small until you realize HOW MANY jobs are exactly this. Someone reading a stack of applications. Someone deciding which support ticket goes to which team. Someone looking at inbound and deciding who's worth calling back. A few ideas on what it unlocks: 1/ Instant quotes that are actually instant. Every quote form on the internet says "we'll email you by end of day." Build the version that answers in under a second, for roofers, movers, insurance, legal intake. 2/ Lead scoring as a product. Every agency and service business has a contact form full of junk. Score every submission and send the real ones straight to the owner's phone. 3/ Support triage for companies with no support team. The ticket gets classified and routed before anyone opens it. 4/ Clipping tools. Pass in a transcript, get the best moments scored in three seconds. Every clipping product just got a cheaper engine. 5/ Application piles. Grants, permits, insurance claims, job apps, loan docs. Someone reads that stack one item at a time today. 6/ Marketplace matching. Someone types what they need and gets matched to the right local business instantly instead of waiting for callbacks. 7/ Browser agents that actually move FAST. That makes bulk browser work practical: pulling quotes from five carriers, filing the same form for 200 clients, checking supplier inventory in real time etc. TLDR; find an expensive queue and put Jev at the front of it. HOW TO GET IT I didn't realize you can skip the waitlist because Jev is live on the Vercel AI Gateway right now, so you can start calling it today. In this episode, we share how. Episode now live on @startupideaspod (thanks to @ryanvogel for coming on and spilling the sauce today) Watch: https://www.youtube.com/watch?v=4mTLpuQpB80 Jev is a big deal because this is a whole new way to do AI Really cool Happy Jev day.
Guidex.com
What Jev is, and the businesses it unlocks
Greg Isenberg: find an expensive queue and put Jev at the front of it. Seven ideas, from instant quotes to lead scoring, plus a Startup Ideas Pod episode with Ryan Vogel.
Live siteOpen source
laya-browser
Laya fine-tuned into the decision head of a browser agent.
cklxx
100% (54/54)
Live siteOpen source
Jev-Style 0.8B Decision v3
Jev-style decisions on a laptop, 0.53 GB in 4-bit.
chaoliangUNSW
0.53 GB
Our guidemadewithjev.com
Jev agent orchestration
Who goes next, is this good enough, should we retry, when does a person step in. Grok Bot ships the workers; a Jev router answers the fork. The three shapes it takes, and where the evidence stops.
Live siteOpen source
autotrust/JEV-9B
An open student of Jev 1.13 with System 1 and System 2 in one set of weights.
AutoTrust
≈ 0.019
Live siteOpen source
System One scorer
Qwen3.5-4B with a scoring head, type-safe by construction.
pngwn
0.922
Live siteOpen source
OpenThai-SystemOne
An open Thai and English System One decision model.
iApp Technology
0.8B
Guidedocs.typesafe.ai
Quickstart: state, questions, typed answers
The three question types, Choice, Score and Noul, in one support-ticket example.
Live siteOpen source
mini-Jev
A frozen Qwen3-0.6B plus a 1.1 MB head for tool selection.
samatv256
~1.1 MB
The newest Jev builds, by the day they were added
Same directory, different order: the entries added most recently, rather than the curated order the home page opens in. The date on a card is the day it was added here, not the day its author published it — this directory is newer than most of the work in it.