There is no Jev waitlist to join today, because TypeSafe AI reopened sign-ups on 27 September 2026 and you can create an account at console.typesafe.ai without waiting for an approval email.
You can also skip the account completely, because four other routes serve the same Jev model with no queue at all.
I re-checked every one of those routes on 11 October 2026, and I'll show you exactly what I found.
This post is the operator walkthrough, so you'll get the sign-up URL, the five setup steps, the no-account routes and what to do if the door closes again.
I'll also tell you the parts I couldn't verify, because access to this model has changed four times in four weeks.
Is there a Jev waitlist right now?
No, there isn't a Jev waitlist right now.
TypeSafe AI's homepage has no waitlist form on it today.
The top menu only offers the API console, the docs, an enterprise page and a contact link.
TypeSafe's quick start tells you to open the console, log in and create a key, and it doesn't mention a queue anywhere.
The last official word on access came from TypeSafe's own X account on 27 September 2026.
That post said Jev was back, capacity had increased and sign-ups were open.
So the short answers to the four questions people ask me are simple.
- There is no waitlist, so there is nothing to join.
- You sign up at console.typesafe.ai, and the key page lives at console.typesafe.ai/keys.
- The wait is zero today, and the original queue only lasted about six days.
- You can skip the account entirely with four other routes, which I list below.
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 doesn't 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 that your code can act on directly.
There are three question types, and TypeSafe's docs describe them like this.
| Question type | What it does | What comes back |
|---|---|---|
| Choice | It picks one option from a list you supply. | You get the choice, a probability for every option and a confidence number. |
| Score | It rates the state against ordered levels you define. | You get the score, a probability for every level and a confidence number. |
| Noul | It answers a yes-or-no question. | You get one probability between 0 and 1 that the answer is yes. |
TypeSafe lists Jev at $0.042 per million input tokens, and output tokens are free.
That price is why operators want in, because every small "which agent takes this?" call stops costing a full chat-model reply.
🔥 Want my exact Jev Waitlist setup, step by step? Inside the AI Profit Boardroom you get step-by-step video trainings, my installable Agent OS and four coaching calls a week with 3,400+ members building real automations. → Join the AI Profit Boardroom
What the Jev waitlist was, and how long it lasted
The Jev waitlist was the early-access queue TypeSafe ran at launch.
TypeSafe's launch post said it was opening early access and bringing developers off the waitlist as quickly as it could.
I sat in that queue myself on launch day.
There was no separate form, because creating a console account and waiting for approval was the waitlist.
Here's the timeline as I understand it, with UK dates.
| Date in 2026 | What happened to access |
|---|---|
| 15 September | Jev launched in early access with a waitlist. |
| 21 September | TypeSafe announced that Jev was available to everyone with no waitlist. |
| 22 September | TypeSafe paused new sign-ups because of demand, and existing accounts kept working. |
| 27 September | TypeSafe posted that Jev was back, capacity had increased and sign-ups were open. |
| 11 October | I found no waitlist form on TypeSafe's site, and the docs point straight to the console. |
TypeSafe said it had cleared roughly 140,000 sign-ups within about 36 hours around launch.
So the original wait was about six days from launch to the queue being removed.
The pause that followed lasted about five days.
I wrote up the first half of this story at the time in my post on how I skipped the Jev waiting list.
This post updates it, because the pause and the reopening both happened after I published that one.
How to get in today: the 5-step setup
This is the direct route, and it gives you the official SDKs and the official endpoint.
Step 1: Open the console
Go to console.typesafe.ai and sign in.
If you made an account during early access, use the same email rather than registering again.
Accounts that existed before the pause kept working the whole time.
Step 2: Create an API key
Open the keys page at console.typesafe.ai/keys and create a key.
Name the key after the project, so you can revoke one key later without breaking another.
Step 3: Store the key outside your code
Put the key in an environment variable called TYPESAFE_API_KEY.
export TYPESAFE_API_KEY="your-key-here"
Don't paste the key into a source file, and don't commit it.
Step 4: Send one small question
TypeSafe's quick start uses this endpoint and the jev-latest model name.
curl -X POST https://api.typesafe.ai/v1/systemone \
-H "Authorization: Bearer $TYPESAFE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "jev-latest",
"state": "Hi, my integration has failed for 3 days and I am losing sales. Please help ASAP.",
"questions": {
"urgency": {
"type": "noul",
"instructions": "Does this message express urgency?"
}
}
}'
The docs say jev-latest currently points to jev-1.13.0.
If a number between 0 and 1 comes back, your key and your network path both work.
Step 5: Check your balance before you build
This is the step that has changed since September.
When the queue was first removed, new accounts started with $5 of credit.
Reports from the reopening say new accounts no longer get that credit for now.
I couldn't confirm the current position from TypeSafe's own docs, and I haven't opened a brand-new account this week.
So look at your balance in the console, and don't plan a project around a free $5 until you can see it.
🔥 Want the agent wiring I use for this? Inside the AI Profit Boardroom, I've got Jev and decision-layer walkthroughs that show how to plug a model like this into a real agent stack. Plus four coaching calls a week and 3,400+ members building real automations. → Get access here
How to skip the Jev waitlist with no TypeSafe account
This is the part I wish somebody had told me on launch day.
The same Jev 1.13 model is served through other doors, and none of them ever had a queue.
I re-checked all four on 11 October 2026.
| Route | Model name | What you need | What I saw on 11 October 2026 |
|---|---|---|---|
| OpenCode Zen free model | jev-1.13-free |
You need nothing, because my call had no key in it. | The call returned HTTP 200 and a real answer in about one second. |
| jevplayground.com | It runs in the browser. | You need no sign-up. | The page said it was free to try and that usage limits apply. |
| Vercel AI Gateway | typesafe-ai/jev |
You need a Vercel account and a gateway key. | The model page was live and listed $0.042 per million input tokens. |
| OpenRouter | typesafe/jev-1.13 |
You need your normal OpenRouter key. | The model page was live at $0.042 per million input tokens with free output. |
The 60-second route: OpenCode Zen
This is the fastest way past any queue, because it needs no account at all.
curl https://opencode.ai/zen/v1/systemone \
-H "Content-Type: application/json" \
-d '{
"model": "jev-1.13-free",
"state": "Customer wrote: please refund my order, it arrived broken.",
"questions": {
"refund": {
"type": "noul",
"instructions": "Is the customer asking for a refund?"
}
}
}'
There is no Authorization header in that request.
When I ran it on 11 October 2026, the answer came back as 0.99 from 286 input tokens.
OpenCode has described this free model as a limited-time offer, so treat it as a trial lane.
The full walkthrough for that route is in my guide to the free Jev API key.
The look-before-you-build route: the playground
jevplayground.com is an independent playground, and it isn't TypeSafe's own site.
It loads four ready-made examples, and you can run one without changing anything.
I'd use it to test the wording of a question before I write any code.
TypeSafe's official playground is at console.typesafe.ai/playground, and that one needs a login.
The gateway routes: Vercel and OpenRouter
If you already pay for one of these gateways, you already have Jev.
On Vercel the model name is typesafe-ai/jev, and the promotional pricing from launch month has ended.
On OpenRouter the model name is typesafe/jev-1.13, and my calls there worked out at roughly $0.00002 each.
You give up the official SDKs on a gateway, but the model behind the door is the same.
My visual guide to the free doors is on agentos.guide as 3 free ways to use Jev AI.
🚀 Ready to put Jev Waitlist to work in your business? Inside the AI Profit Boardroom you get step-by-step video trainings, my installable Agent OS and four coaching calls a week with 3,400+ members building real automations. → Join the AI Profit Boardroom
What to do if Jev sign-ups pause again
TypeSafe has already paused sign-ups once, 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 same note says limits can change as more GPU capacity lands and more users are let in.
Here's the operator setup that makes a pause a non-event.
- Keep the endpoint and the model name in one config value, so a switch is a one-line change.
- Create your TypeSafe account now, because accounts that existed before the last pause kept working.
- Keep one gateway key as a spare, so your agents have a second door.
- Add a retry with backoff, because a request over the limit returns a 429.
- Send anything below your confidence line to a human instead of retrying forever.
That's five small habits, and together they mean a closed sign-up page never stops 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 didn't find one.
TypeSafe's models page lists one current model, which is Jev 1.13.
The page also has a jev-preview alias, and the docs say there's no preview build available right now.
So there isn't a waitlist for a newer or faster Jev that I can verify.
For higher rate limits, the docs say custom and enterprise plans are available by contacting TypeSafe's sales team.
That's a sales conversation and not a waiting list.
If you've seen "Jev Ultrafast" mentioned and wondered whether it has its own queue, I cover what that actually is in the Jev Ultrafast GitHub explainer.
Gotchas and limits once you're in
Getting in is the easy part now, so here's what catches operators afterwards.
- Jev reads text only, so images, audio and video have to 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 numbers can change without notice.
- English is the primary training language, so test carefully before you rely on Jev for other languages.
- An alias such as
jev-latestmoves when a new release ships, so pinjev-1.13.0if you've tuned thresholds against it. - Jev doesn't write prose, so you still need a writing model behind it.
TypeSafe's status page showed all services online when I checked on 11 October 2026.
If you'd rather not depend on anyone's servers, I tested the open-source options in how to run Jev locally.
🚀 Want this running inside a full agent system? The AI Profit Boardroom is where I show the Agent OS, with a decision layer like Jev underneath that routes leads, grades enquiries and picks what each agent does next. You get the walkthroughs, four coaching calls a week and 3,400+ members to compare setups with. → Join the Boardroom here
A real example: the first thing I'd wire up
Start with a triage question on an inbox you already own.
Write one Choice question with four options, which are sales, support, billing and spam.
Run ten real emails through the playground first and read the probabilities.
Then move the same question to the free Zen model and call it from your agent.
Set a confidence line, and send everything under it to a person.
When that works for a week, move the call to your own TypeSafe key and pin the version.
That whole path needs no approval from anyone, which is the opposite of how launch week felt.
If you want the agent side of that stack, my free Hermes Agent OS walkthrough covers it.
Who should use which route
Use the free Zen model if you want a working call in the next minute.
Use the playground if you're still deciding whether Jev fits your problem.
Use Vercel or OpenRouter if your stack already routes through one of them.
Use the TypeSafe console if you're building something customers will touch.
Every route gets you the same model, so pick the door you already have a key for.
Related reading
- Free Jev API key: the keyless route, step by step
- How to run Jev locally, and what you actually get
- Jev Ultrafast on GitHub, explained
- Every door to Jev access, on the AI Profit Boardroom blog
📺 Video notes + links to the tools 👉
🎥 Learn how I make these videos 👉
🆓 Get a FREE AI Course + Community + 1,000 AI Agents 👉
Also On Our Network
- 🌐 What the end of the Jev queue means for a small business
- 🌐 My verdict on every way into Jev, scored
- 🌐 The 60-second Jev quick start for an Agent OS
- 🌐 Which benched models to pair with Jev once you're in
About Julian
I'm Julian Goldie, an AI entrepreneur, SEO expert, and founder of the AI Profit Boardroom, which has 3,400+ members.
I help business owners scale with AI agents, automation, and SEO.
- I have 400,000+ YouTube subscribers who watch my AI tool tests every week.
- I built a 7-figure agency from the ground up.
- I run daily AI training inside the Boardroom.
- I wrote two Amazon best-sellers on SEO and agency growth.
→ Get my best AI training inside the AI Profit Boardroom
Jev Waitlist 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 when I checked on 11 October 2026.
How do I join the Jev waitlist?
You don't need to, because there isn't one to join. Sign in at console.typesafe.ai and create a key on the keys page. If sign-ups ever pause again, use OpenCode Zen, Vercel AI Gateway or OpenRouter instead.
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. The sign-up pause that followed lasted about five days.
Can I skip the Jev waitlist completely?
Yes. The OpenCode Zen model called jev-1.13-free answered my keyless call on 11 October 2026. The independent jevplayground.com needs no sign-up, and Vercel AI Gateway and OpenRouter both serve Jev with their own keys.
Do new Jev accounts still get $5 of free credit?
Reports from the reopening say the $5 credit is switched off for new accounts for now. I couldn't confirm that from TypeSafe's own docs, so check your console balance before you plan around it.
Is there a waitlist for Jev enterprise or a newer Jev model?
I couldn't find one. TypeSafe's docs list Jev 1.13 as the current model, say there's no preview build right now, and tell you to contact sales for higher limits on custom and enterprise plans.
The bottom line
The queue is gone, the console is open, and four other doors serve the same model if it ever closes again.
Make the account today, keep a spare route in your config, and build with a confidence line from the first call.
That's everything an operator needs to know about the Jev waitlist.
