agentos.guide › blog

Jev Waitlist: There Isn't One Now, And Here Is The 60-Second Way In

By Julian Goldie · 7 October 2026 · agentos.guide

There is no Jev waitlist to join in October 2026, because TypeSafe AI reopened sign-ups on 27 September and you can create an account at console.typesafe.ai today.

You can also skip the account completely, because the free OpenCode Zen model answered my keyless call on 11 October 2026.

The questions I keep getting are simple: is there a queue, how do I join, how long is it, and can I skip it?

I will answer all four, give you a 60-second quick start, and show you where Jev belongs in an Agent OS once you are in.

The Jev waitlist answers at a glance

Here are the four answers before any detail.

Everything below explains those four lines and shows you the quickest way in.

What Jev is, and who makes it

Jev is a decision model made by TypeSafe AI, and it launched in early access on 15 September 2026.

It does not write text.

You send it a "state", which is the email, ticket or log you want judged, plus one or more typed questions.

It sends back typed answers with probabilities, so your agents can act on them without reading prose.

TypeSafe's docs list three question types.

• A Choice question picks one option from a list you supply and returns a probability for every option.
• A Score question rates the state against ordered levels that you define.
• A Noul question answers yes or no and returns one probability between 0 and 1.

TypeSafe lists Jev at $0.042 per million input tokens, and output tokens are free.

That price is the reason so many people rushed the queue in launch week.

What the Jev waitlist was, and how long it lasted

The Jev waitlist was the early-access queue that TypeSafe ran when the model launched.

TypeSafe's launch post said it was opening early access and bringing developers off the waitlist as quickly as it could.

There was no separate form, because creating a console account and waiting for approval was the waitlist.

I joined on launch day and waited with everyone else.

TypeSafe said it had cleared roughly 140,000 sign-ups within about 36 hours.

Here is the timeline with UK dates.

The original queue lasted about six days, and the pause that followed lasted about five.

Some sites show these dates a day earlier, because TypeSafe posts in US time.

I wrote about the first half of this story in how I skipped the Jev waiting list, which went live before the pause.

The 60-second quick start that needs no Jev waitlist and no account

This is the fastest way to get a real Jev answer, and it needs nothing but a terminal.

Send a POST request to https://opencode.ai/zen/v1/systemone.

Set the model to jev-1.13-free.

Put the text you want judged in the state field.

Add one question with the type set to noul and a plain-English instruction.

I ran exactly that on 11 October 2026 with no key in the request.

My state was a customer message asking for a refund on a broken order.

My question was "Is the customer asking for a refund?".

The answer came back as 0.99 from 286 input tokens, and the round trip took about one second.

OpenCode has described this free model as a limited-time offer, so treat it as a trial lane and not a forever plan.

If you want to look before you type anything, jevplayground.com is an independent playground that needs no sign-up.

It loads ready-made examples, and its page says usage limits apply.

🔥 Want the exact Jev access setup I run inside my Agent OS?

Inside the AI Profit Boardroom you get the installable Agent OS, step-by-step video tutorials, four coaching calls a week and 3,400+ members building real automations.

→ Get access here

How to join through the TypeSafe console

There is no waitlist form to fill in, so joining now means creating an account.

• First, sign in at console.typesafe.ai.
• Second, open the keys page at console.typesafe.ai/keys and create an API key.
• Third, store the key in an environment variable called TYPESAFE_API_KEY.
• Fourth, send a request to https://api.typesafe.ai/v1/systemone with the model set to jev-latest.
• Fifth, check your balance in the console before you plan any volume.

The docs say jev-latest currently points to jev-1.13.0.

If you created an account during early access, sign in with the same email, because accounts made before the pause kept working.

There is one honest caveat on the fifth step.

When the queue was first removed, new accounts started with $5 of credit.

Reports from the reopening say that credit is switched off for new accounts for now.

I could not confirm the current position from TypeSafe's own docs, and I have not opened a brand-new account this week.

So read your console balance and plan from what you can see.

Every route past the Jev waitlist, side by side

I re-checked all five doors on 11 October 2026.

All five lead to the same Jev 1.13 model.

The direct route gives you the official Python and JavaScript SDKs and lets you pin a version.

The gateway routes are quicker if you already hold one of those keys.

My calls through OpenRouter worked out at roughly $0.00002 each.

Vercel's promotional pricing from launch month has ended, so that door now charges the normal rate.

The longer walkthrough of the free doors, with screen recordings, is in my Jev AI free guide.

The key-by-key breakdown is in the free Jev API key post.

Where Jev sits in an Agent OS once you are in

Getting access is only useful if you know where the model goes.

In an Agent OS, Jev is not an agent.

It is the decision layer that sits in front of your agents.

Every incoming job gets a quick typed question before any large model sees it.

A Choice question decides which agent or which model should take the job.

A Noul question decides whether an action is safe to run without a person.

A Score question decides how urgent a job is, so the queue sorts itself.

Only the jobs that need writing or building go on to Claude, Hermes or another large model.

That is how you stop paying a writing model to answer yes-or-no questions.

TypeSafe's docs describe the same idea as confidence-gated routing.

The answer tells you what to do, and the confidence tells you whether to act on it.

I tested this properly in my Jev model routing guide, where clearer criteria lines made a big difference to accuracy.

🔥 Want the exact Jev access setup I run inside my Agent OS?

Inside the AI Profit Boardroom you get the installable Agent OS, step-by-step video tutorials, four coaching calls a week and 3,400+ members building real automations.

→ Get access here

How to make your Agent OS survive another sign-up pause

TypeSafe has paused sign-ups once already, so I build as if it could happen again.

The docs still say rate limits are adjusting dynamically while TypeSafe serves a very large volume of demand.

The fix is a fallback order that lives in your config.

Here are the habits that make that table work.

• Keep the endpoint and the model name in one config value, so switching routes is a one-line change.
• Create your TypeSafe account now, because existing accounts kept working through the last pause.
• Add a retry with backoff, because a request over the limit returns a 429.
• Log which route answered each job, so you can compare them later.
• Pin jev-1.13.0 once you have tuned your thresholds, because an alias moves when a new release ships.

With that in place, a closed sign-up page becomes a non-event for your agents.

Is there a Jev waitlist for a new tier, a preview or enterprise?

I looked for every other queue I could think of, and I did not find one.

TypeSafe's models page lists one current model, which is Jev 1.13.

The page has a jev-preview alias, and the docs say there is no preview build available right now.

So I cannot verify a waitlist for a newer or faster Jev.

For higher rate limits, the docs say custom and enterprise plans are available through TypeSafe's sales team.

That is a sales conversation and not a waiting list.

If you have seen the name "Jev Ultrafast" and wondered whether it has its own queue, I explain what it is in the Jev Ultrafast GitHub guide.

Limits to know before you wire Jev in

Access is easy now, so the limits matter more than the door.

• Jev reads text only, so images, audio and video must be turned into text first.
• The docs give a budget of 64,000 tokens per request, with 32,000 for the state plus the longest question.
• The docs list rate limits of 100,000 tokens per second and 80 requests per second, and they warn those can change without notice.
• English is the primary training language, so test other languages on your own content.
• Jev does not write prose, so it never replaces the writing model behind it.
• A free route can change at any time, so never put one on a critical path.

TypeSafe's status page showed all services online when I checked on 11 October 2026.

If you would rather not depend on anyone's servers, I tested the open-source options in my run Jev locally post.

What I could not verify

I would rather tell you this than guess.

• I could not load the console sign-up screen with a script, because it sits behind a browser security check.
• I am relying on TypeSafe's own X post and its docs for the sign-up step.
• I could not confirm the $5 credit position from TypeSafe's docs, so that detail comes from reports.
• TypeSafe's homepage still describes Jev as being in early access, and I found no statement about full general availability.

Check your own console before you rely on any of those points.

What to do next

Run the 60-second quick start with one question from your own business.

Create your TypeSafe account while the door is open.

Put the fallback order in your config before you need it.

If you want the whole decision layer already wired into an Agent OS, with the tutorials and four coaching calls a week, it lives inside the AI Profit Boardroom.

FAQ

Is there still a Jev waitlist?

No. TypeSafe AI removed the queue on 21 September 2026, paused sign-ups a day later and reopened them on 27 September 2026. There was no waitlist form on TypeSafe's site on 11 October 2026.

How do I join the Jev waitlist?

There is nothing to join. Sign in at console.typesafe.ai and create a key on the keys page. If sign-ups pause again, use the OpenCode Zen free model, Vercel AI Gateway or OpenRouter.

How long was the Jev waitlist?

The original queue ran for about six days, from the launch on 15 September 2026 to its removal on 21 September 2026. A sign-up pause then lasted about five days.

Can I skip the Jev waitlist?

Yes. The OpenCode Zen model called jev-1.13-free answered a keyless call on 11 October 2026, the independent jevplayground.com needs no sign-up, and Vercel AI Gateway and OpenRouter serve Jev with their own keys.

Do new Jev accounts still get $5 of free credit?

Reports from the reopening say the credit is switched off for new accounts for now. That could not be confirmed from TypeSafe's own docs, so check your console balance.

Where does Jev sit in an Agent OS?

Jev is the decision layer in front of your agents. It answers the small pick-one, yes-or-no and score questions, and only the jobs that need writing go on to a large model.

Final word on the Jev waitlist

The queue is gone, the console is open, and the keyless route gets you a real answer in about a minute.

Make your account now, keep a fallback route in your config, and you will never be stuck behind a Jev waitlist.

Related guides on agentos.guide

→ 3 Free Ways To Use Jev AI Right Now

→ Free Jev API Key: Every Way In

→ Jev AI Model Routing: The Real Test

📺 Video notes + links to the tools 👉

🎥 Learn how I make these videos 👉

🆓 Get a FREE AI Course + Community + 1,000 AI Agents 👉

← all guides on agentos.guide