Jev and System One models: what they mean for sales teams

TypeSafe's Jev answers typed questions in milliseconds instead of writing text. What it is, where it fits in a sales stack, what it cannot do, and how to test it on your own pipeline.

On 15 September 2026, TypeSafe AI released Jev into early access, alongside a $40 million seed round led by DCVC. TypeSafe was founded by Diogo Almeida, a former OpenAI researcher, and Jev is the first model in a class the company calls System One models.

Most coverage has been about the speed claims. For a sales team the more useful point is simpler. Most of the AI in a sales stack is not writing anything. It is deciding: which rep gets this lead, is this reply a meeting request or a brush-off, is this deal stalling. Those are the jobs Jev was built for, and it is worth knowing where it fits before a vendor tells you.

What Jev actually is

A language model answers in prose, one token at a time, and your software has to read the prose back. Jev skips the prose. You send it a block of state, for example an email and the account’s record, plus a set of typed questions, and it returns typed answers:

  • A choice from a list of options you define, such as which of six queues a lead belongs in.
  • A score against a rubric, such as how urgent a reply is.
  • A yes or no, such as whether a message asks for a meeting.

Each answer comes with a calibrated probability. Calibrated means the numbers are meant to be honest: across many decisions, the ones Jev gives 90% should be right about nine times in ten. That is what makes it usable in software. You can act automatically above one threshold and send everything below it to a person, instead of trusting every answer the same.

The name is a double reference. System One comes from Daniel Kahneman’s fast, intuitive System 1 thinking. Jev comes from William Stanley Jevons, whose paradox says that when something gets cheaper, people use far more of it.

The numbers, and how to read them

$42

per billion input tokens, with output free TypeSafe's published early-access price for Jev, which is $0.042 per million input tokens. Output is free because Jev returns a choice, a score or a probability instead of generated text. Early-access prices can change. TypeSafe AI, Introducing System One Models and Jev
ClaimWhat TypeSafe reports
Latency70 to 500 milliseconds, end to end
Speed against a language model20 to 200 times faster on decision-shaped workflows
Cost against a language model40 to 400 times cheaper on the same workflows
Price$42 per billion input tokens, output free

The multipliers come from TypeSafe’s own comparisons on its chosen workflows. Read them as what is possible on a decision-shaped task, not as a promise for yours. The latency range is the number that matters for anything live: under half a second is fast enough to use while a buyer is still talking.

Where it fits in a sales stack

The test is whether the job is a decision with a known set of answers, made many times.

JobThe typed questionWhy it fits
Routing inbound leadsWhich rep or queue should take this?Runs on every form fill, and the options are fixed
Sorting repliesMeeting request, objection, referral, unsubscribe or out of office?A choice from five, thousands of times a week
Deal riskHow stalled is this deal, given the last month of activity?A score against a rubric you already use
CRM hygieneDoes this reply say the contact has left the company?A yes or no, with a threshold before anything changes
Buying signalsHow strongly do these notes point to a purchase this quarter?A score you can sort a list by
The live callWhich kind of objection did the buyer just raise?A choice that has to be made in well under a second

What it cannot do

This is where most of the value of knowing about Jev is, because it keeps a team from buying the wrong thing.

  • It does not write. No emails, no call replies, no summaries, no chat. Anything a buyer reads still needs a language model or a person.
  • It does not reason in steps. A multi-part judgment has to be broken into single questions in your own code.
  • It reads text only. No audio, images or video, so a call has to become a transcript or captions first.
  • It does not explain itself. You get a number, not a reason, which matters when a manager asks why a lead was routed away from them.
  • It only knows what you send it. It does not browse or look anything up, so the account context has to be in the request.
  • It can struggle with arithmetic, counting and dates. Keep those calculations in your code.

Decide fast, then write

The useful pattern is two steps. A fast model decides what is happening and whether anything needs to happen. A generative model, or a person, writes only when it does. Most messages need a decision and never a paragraph, so the expensive step runs far less often.

A live sales call is the clearest case, because the time budget is a few seconds. Recognizing that the buyer just raised a timing objection is a decision, and a System One model can make it in a fraction of a second. Writing a reply that mentions the buyer’s own business, in the seller’s voice, is generation, and it is where the rest of the time goes. That is the split Axelize is built around: it recognizes the moment, then writes the sentence while the buyer is still talking.

On a discovery call, Johanna Lorenz from Fourth Coffee says: “We'd love to, but let's revisit this after the holidays.” Axelize finds: Fourth Coffee is opening four new stores in November, and its hiring page lists twelve open roles for them. It suggests: “Totally understand. You're opening four stores in November, though, so is the question whether the new teams start on this or get moved over later?” Recognizes a timing objection, then ties it to a date the buyer already has, so waiting has a visible cost.

An example with a fictional company. The objection type is the decision; the reply is the part that has to be written.

Get replies like this on your own calls

How to test it on your own pipeline

  1. Pick one decision your team makes more than 100 times a week. Lead routing and reply sorting are the usual first choices.
  2. Write it as one typed question with the exact options you would accept, including an “other” or “none” option.
  3. Pull 50 to 100 past examples where you already know the right answer.
  4. Check the calibration. Of the answers it gave at around 90%, were about nine in ten right? If not, the probabilities cannot drive automation yet.
  5. Set two thresholds. Act automatically above one, send to a person below the other, and look at what lands between them.
  6. Cost it. Tokens per decision, times weekly volume, times $0.042 per million. Sorting 10,000 inbound emails of about 500 tokens each is 5 million tokens, which is about $0.21 at the listed price.

Sources

The figures above are TypeSafe’s own, as published in its announcement and reported in the coverage below, as of 26 September 2026: Introducing System One Models and Jev; the funding coverage in Forbes and SiliconANGLE; and DataCamp’s explainer, Jev: TypeSafe’s System One Model.

Robinzon Sokhashvili

Founder, Axelize

Founder of Axelize. Writes about the few seconds after a buyer objects, and the tools that help or get in the way.

BuyerSo what would this look like on our calls?

Axelize On Google Meet

Your next sentence, while the buyer is still talking.

Axelize reads the call's live captions and writes the reply in your own words. No bot joins the meeting, and no audio or video is recorded.

Want more of these in your Google results? Add as preferred source

Frequently asked questions

What is a System One model?
TypeSafe's name for a model that makes fast, structured decisions instead of generating text. It takes the state you give it and returns a typed answer, such as one option from a list, a score or a yes or no, with a probability attached. The name borrows Daniel Kahneman's System 1, the fast and intuitive mode of thinking.
How much does Jev cost?
TypeSafe lists Jev at $42 per billion input tokens, which is $0.042 per million, with output free, because Jev returns a decision rather than generated text. It is in early access, so the price may change.
Can Jev write sales emails or call replies?
No. Jev does not generate text at all. It can decide which reply template fits, whether a reply is needed, or how urgent it is. The email itself still needs a language model or a person.
Does Axelize use Jev?
No. Axelize runs the same two steps on a live call, recognizing what the buyer just said and then writing the seller's reply, with its own pipeline. The second step is the one a System One model does not do.

Keep reading