Independent Jev ecosystem hub
Learn TypeSafe Jev, discover real-world projects, explore integrations, follow ecosystem updates, and build with practical examples and developer tools.
Real request shape from TypeSafe's quickstart
{
"model": "jev-latest",
"state": "Hi, I've been trying to connect my Stripe account for 3 days and the integration keeps failing. I'm losing sales. Please help ASAP.",
"questions": {
"department": {
"type": "choice",
"instructions": "Which team should handle this",
"criteria": {
"billing": "Payment or subscription issues",
"technical": "Bugs or integration problems",
"sales": "Pricing or account questions"
}
},
"is_urgent": {
"type": "noul",
"instructions": "The message conveys urgency or time-sensitivity"
}
}
}Jev is a System One Model developed by TypeSafe for fast structured decisions such as classification, routing and scoring. You send a state — a string, JSON object, or array of text — plus typed questions. Jev returns answers your code can use directly: a selected option, a rubric score, or a yes/no probability. It is not a chatbot and it does not write replies. TypeSafe is the vendor; Jev is the model; System One is the model class.
Includes applications that call hosted Jev, independent models with compatible APIs, and related libraries. A listing does not imply a TypeSafe partnership.
Updated SDK guidance for Python 0.7.5 and JavaScript 0.7.0, added model migration and experimental image guides, and corrected content dates, page titles, sitemap duplicates, and RSS identifiers. Examples distinguish illustrative output from live measurements.
Updated guides and pricing config for jev-1.14.0 and the jev-preview alias, documented long-context headers and per-organization rate limits, refreshed GitHub star counts for published ecosystem projects, expanded the sitemap with /pricing/, /api/, and /getting-started/, and added a default Open Graph image plus an optional IndexNow postbuild hook.
TypeSafe published jev-1.14.0 on the models page. Input pricing matches jev-1.13.0 ($0.042 per million input tokens, output free). jev-latest still points at jev-1.13.0; jev-preview now points at jev-1.14.0. Long context (262k limits) is available on both versions via the TypeSafe-Danger-Zone-Long-Context header. Public rate-limit numbers were removed in favor of per-organization limits in the developer console.
New profiles for Kev, Laya, Von, SemIf, AnyJev, NanoJev, jevc, pi-jev-auto-mode, and jevmetrics, plus guides for the open-source landscape, coding-agent gates, confidence routing, composite scoring, and the official pattern and cookbook index. GitHub star counts were captured from the GitHub API on this date. Author-reported accuracy stays labeled as author-reported.
The official models page still lists jev-1.13.0 at $0.042 per million input tokens, with output tokens free. jev-latest and jev-preview both still point at jev-1.13.0. There is no model named Jev 1.3. The same page now lists 100,000 tokens per second and 40 requests per second, and says those limits can move while demand is high.
Jev is TypeSafe's flagship System One model. You send a state and typed questions; it returns structured answers, probabilities, and, for Choice and Score, confidence.
TypeSafe AI is the company that builds Jev. TypeSafe is the vendor; Jev is the model; System One is the model class.
No. Jev AI Hub is an independent educational resource. It is not affiliated with or endorsed by TypeSafe.
No. Jev understands natural-language input but does not generate prose, code, or explanations. It returns Choice, Score, and Noul answers your code can branch on.
Existing TypeSafe accounts use a console key. New direct signups were paused on 2026-09-24; OpenRouter and Vercel AI Gateway still document a path. Then POST state plus typed questions. Start with How to Use Jev.
These text decision primitives select an option, rate on a rubric, or return a yes/no probability. Experimental Box questions locate a target in an image on Jev 1.14.
When last verified, official docs listed $0.042 per million input tokens, with output tokens free. Check the pricing page and TypeSafe's models page before budgeting.
The hosted model is not. TypeSafe publishes the API and the SDKs. Independent projects such as Kev, Laya, and Von serve the same request shape with their own weights. The writeup is at /jev/open-source/.
Official docs say Jev is not fine-tuned or LoRA-adapted with customer data. You shape answers through state, instructions, and criteria.