Jev is TypeSafe AI's System One frontier model: unstructured state in, typed probabilistic decisions out. Instead of generating text, Jev returns Choice, Score, and Noul answers with calibrated probabilities your code can act on. Parallel sampling delivers ~70-500ms responses, about 20-200x faster and 40-400x cheaper than comparable LLM workflows, with output tokens free. Now available to everyone at console.typesafe.ai with no waitlist.
Forum Threads
92 emails in my inbox, 2 left after Jev sorted them
I run 10+ products solo and read the support inboxes myself. After a press release for one of them, the contact address got buried in pitches: webinar invites, free whitepapers, agencies wanting to run my ads. Gmail filters didn't hold. Senders change every time, and "thank you for your inquiry" shows up in both auto-replies and real human replies.
The worst ones borrow a platform. Someone shares a pitch as a Google Doc, so the email comes from Google. Or they sign you up for their Zoom webinar, so the invite comes from Zoom. You can't send Google or Zoom to spam.
Jev is what finally fixed it. It doesn't write anything, it just tells you how likely each yes/no answer is, and you decide where the line goes. Per email I ask five yes/no questions in one call: did a person write this, should we reply, are they selling us something, do they want a meeting, are they clearly asking us to stop. A few rules around it:
Ask twice, act only if both agree. Otherwise I look myself.
I use Jev as a judge for whether my AI coding agent's tests really passed!
Hi, I'm Rikin, maker of dotpals (a small open-source pal that shows what your AI coding agents did). Most people seem to use Jev for lead-gen and booking calls. I'm using it for something different: as a judge for test results. My coding agent says "All tests pass. Done!" far too often. dotpals reads the test runner's own output first, and when the output and the exit code disagree, it sends Jev a short, redacted snippet and asks one question: "did these tests pass?"
It answers in about 0.2 seconds with a probability. In the first day it caught a real false "pass" (a run where the tests never actually ran) at 92% certainty, and it rated our own 148-test suite as passed, 98% sure.
OpenAI
Hey PH community 👋
Excited to hunt Jev today.
Jev from Typesafe is taking over the tech community like the first launches of ChatGPT, Claude Code, and the drops that made everyone stop and rebuild what they were shipping.
Jev is now open to everyone. No waitlist. Start in the console:
https://console.typesafe.ai
Jev is TypeSafe AI's System One model for typed decisions, not chat. You send unstructured state and get Choice, Score, and Noul answers with calibrated probabilities your software can act on. Parallel sampling lands those judgments in about 70 to 500ms, roughly 20 to 200x faster and 40 to 400x cheaper than comparable LLM workflows, with output tokens free.
I luckily had early access via the Netlify AI Gateway, traded some sleep this weekend, and built an arcade for Typesafe's Jev. [Not one but 7](https://jevarcade.netlify.app/) interactive games that show what it can do.
Typesafe's open access post:
https://x.com/typesafeai/status/...
Release blog with the receipts:
https://typesafe.ai/blog/introdu...
Tagging @diogo_almeida if you're here.
Give the console a spin, try a game, and tell the team which decisions you want to automate with Jev 🚀
Hey @thisiskp_ , congrats on the launch!
Excited to try it out.
@mangomangoosy it’s all the rage. Try it out!
Enjoying Jev so far. I used Jev to create an AI business partner. It helps with decisions before forwarding to openrouter. I like that it is able to challenge me, disagree, and give better advice. Not a yes men like using just LLMs.
I've been following this team for a while and it's pretty exciting to see it taking the internet by storm. The model itself is pretty good. We're evaluating it internally and it's super impressive! So fast.
For uses as a classifier it’s just…better. More reliable, way faster and cheaper.
Doesn’t do chat or code
They post trained LLMs to work like machines instead of please humans (“RLCD” vs RLHF)
It outputs json. Categories and probabilities. Not tokens in sequence. And it outputs huge jsons nearly instantly and for free.
@rajiv_ayyangar the ability to fire jsons in parallel is epic too. Thanks for your comment! Love that you all are testing Jev internally. Could be fun to let Jev classify reviews into buckets instantly.
Hii @thisiskp_ Excited to try this. One usecase i think is with trying it on enterprise knowledge graph and ontologies built on antcluster. Its like putting probablities in case of determinism.
How is Jev different from Open Source alternatives like Laya?
I loved the onboarding process! And the whole approach is finally something fresh in the AI field. I'm already integrating that into my tools 🙌