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.
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:
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.
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.
Report
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.
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.
Report
How is Jev different from Open Source alternatives like Laya?
Report
Will definitely use this more. I got early access on their site from the waitlist and it was great.
Netlify
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 🚀
QuietHint®
Hey @thisiskp_ , congrats on the launch!
Excited to try it out.
Netlify
@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.
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.
Product Hunt
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.
Netlify
@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.
How is Jev different from Open Source alternatives like Laya?
Will definitely use this more. I got early access on their site from the waitlist and it was great.