> ## Content Index
> Fetch the complete content index at: https://airabbit.blog/llms.txt
> Use this file to discover other available public pages before exploring further.

# Decision Models Are Quietly Replacing a Chunk of LLM Infrastructure
- URL: https://airabbit.blog/decision-models-the-ai-shift-most-people-havent-noticed-yet/
- Published: 2026-10-15T19:04:04.000Z
- Updated: 2026-10-15T20:33:26.000Z
- Author: AiRabbit

There's a new trend in AI that's already changing how the AI economy works. But most people outside tech haven't heard of it yet.

It's called **decision models**.

Within 16 days, [TypeSafe launched Jev](https://typesafe.ai/blog/introducing-system-one-models-and-jev?ref=airabbit.blog) (September 15), [OpenAI announced a Decisions API](https://thenewstack.io/openai-decision-api-luna/?ref=airabbit.blog) in limited preview (September 29), and [Cloudflare shipped two open-source decision models called Clef](https://blog.cloudflare.com/clef-decision-models?ref=airabbit.blog) (October 1).

It sounds like technical stuff. In a nutshell, the idea is pretty simple.

With a normal AI chat, you describe what you want in plain language and the AI is free to write whatever it wants back. With a decision model, you narrow the answer down to a short list of options you define. The model just picks one, and tells you how sure it is.

That's it. No essay. No "Certainly! Here's…". A choice and a probability.

![How a decision model works](https://storage.ghost.io/c/b6/58/b65880bb-2a06-491e-bb4d-a6abeb13a649/content/images/2026/10/data-src-image-ef96288e-02d9-4bf6-a588-a746699be08c.png)

The model never writes text. It only scores the answers you allowed.

## "Isn't That Just Multiple Choice?"

Yes. And that's exactly why it matters.

At first glance it sounds like something very niche, like a multiple-choice exam. But if you think about it, a huge amount of what we ask AI to do every day already is a decision. We just phrase it as an open question.

- "Is this email a scam?" is yes or no.
- "Which team should handle this ticket?" is one of five teams.
- "Which button should I click on this page?" is one of the 40 buttons on the page.
- "How urgent is this?" is a point on a scale.

You don't need a new problem. You need to say the problem you already have in a different way.

## Why Bother? Speed and Cost

Because the difference isn't small.

TypeSafe says Jev's "end-to-end response time is 70ms-500ms" and input costs $0.042 per million tokens, with output tokens free ([typesafe.ai](https://typesafe.ai/blog/introducing-system-one-models-and-jev?ref=airabbit.blog)). In [OpenRouter's Jev tutorial](https://openrouter.ai/docs/guides/community/jev-tutorial?ref=airabbit.blog), a call that answers three questions about a support ticket at once cost $0.00002.

For comparison: a normal language model has to write out its answer word by word, and you pay for every word. A decision model scores all the options in one pass and stops.

Those are vendor numbers. But I raced Jev against Cloudflare's two Clef models myself, like I wrote in [a previous post](https://airabbit.blog/cloudflare-just-shipped-two-decision-models-i-raced-them-against-jev/), and Jev was the fastest on every task I gave it.

Fast enough that it stops feeling like "calling an AI". It feels like calling a function.

And honestly, I think this will replace a good chunk of the LLM infrastructure people have built for these jobs. Not the writing. The deciding.

## What You Can Already Do With It

Here are a few examples that are already getting real traction:

- **Clicking through websites.** Browser Use built an agent called `jev-ultrafast` that looks at every page as a numbered list of buttons and fields, then asks Jev two questions at once: what to do, and on which element ([github.com](https://github.com/browser-use/jev-ultrafast?ref=airabbit.blog)). What used to need a large language model to "think" about the page is now a pick from a list.
- **Spotting scams and phishing.** Cloudflare uses Clef to fetch a website, look at it and classify it. Its example output literally reads "<1% phishing" ([blog.cloudflare.com](https://blog.cloudflare.com/clef-decision-models?ref=airabbit.blog)). The same pattern works for your inbox: is this email dangerous, yes or no, in near real time.
- **Good bot or bad bot.** Cloudflare also uses it to decide whether a crawler hitting a website is a good bot or a bad one ([blog.cloudflare.com](https://blog.cloudflare.com/clef-decision-models?ref=airabbit.blog)).
- **Routing support tickets.** Which team, how urgent, is it a bug. Cloudflare triages its own support requests this way ([blog.cloudflare.com](https://blog.cloudflare.com/clef-decision-models?ref=airabbit.blog)), and it's the example in [OpenRouter's Jev tutorial](https://openrouter.ai/docs/guides/community/jev-tutorial?ref=airabbit.blog).
- **Guardrails for AI agents.** Before an agent runs a command: is this safe, yes or no. TypeSafe lists guardrailing and detecting jailbreaks as core uses ([typesafe.ai](https://typesafe.ai/blog/introducing-system-one-models-and-jev?ref=airabbit.blog)).
- **Picking the right passage.** In one of my own apps, Jev picks the best passages from PDF manuals before an answer is written ([my race post](https://airabbit.blog/cloudflare-just-shipped-two-decision-models-i-raced-them-against-jev/)).

There are many more. Anything where the answer is "one of these" is a candidate.

So if you haven't come in contact with decision models yet, I think now is the time to start understanding them and trying them out.

## It Goes Further: Your Own Model, on Your Own Machine

Clef is open source under the Apache 2.0 license, and the weights are [on Hugging Face](https://huggingface.co/Cloudflare/clef?ref=airabbit.blog). Cloudflare says it's released "for you to run locally and experiment with yourselves" ([blog.cloudflare.com](https://blog.cloudflare.com/clef-decision-models?ref=airabbit.blog)).

There are even smaller ones. [Laya from Convai Innovations](https://aiweekly.co/alerts/convai-ships-laya-a-421m-modernbert-decision-model-apache-20?ref=airabbit.blog) has 421M parameters, is also Apache 2.0, and is small enough for a laptop. The catch: its own model card warns it's weak out of the box, so you fine-tune it on your own examples first.

Fine-tuning is getting easier too. Cloudflare now offers to fine-tune Clef for your workload with its own team, and says a self-serve platform to "capture data, fine-tune, and redeploy the model" is planned ([blog.cloudflare.com](https://blog.cloudflare.com/clef-decision-models?ref=airabbit.blog)).

Think about that for a second. A model that makes your decisions, trained on your data, running on your own machine, answering in milliseconds.

## How to Try It

The easiest way is [OpenRouter](https://openrouter.ai/?ref=airabbit.blog), a single account that gives you access to hundreds of AI models. Jev, Clef and Clef-flash are all on it. No waitlist and no separate sign-up with TypeSafe.

Or go directly to [TypeSafe](https://typesafe.ai/?ref=airabbit.blog) for Jev, or to [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/models/clef/?ref=airabbit.blog) for Clef. OpenAI's Decisions API started as a limited preview for selected customers ([thenewstack.io](https://thenewstack.io/openai-decision-api-luna/?ref=airabbit.blog)).

And this is just the start. The ecosystem is growing fast: three big launches in 16 days, and more alternatives keep showing up.

## The Limitations

- **It can't write.** If you need a text answer, you still need a normal language model. Browser Use's agent uses a small text model on the side just for typing.
- **You have to know the options.** If the right answer isn't on your list, the model can't invent it. That's the point, and also the catch.
- **Most numbers are launch claims.** Speed, price and "it can't hallucinate" come from the vendors. TypeSafe itself says its 0% hallucination number "is not empirical" ([typesafe.ai](https://typesafe.ai/blog/introducing-system-one-models-and-jev?ref=airabbit.blog)). In my own test, Cloudflare's speed claims didn't hold up against Jev.
- **Confidence isn't always useful.** In my race, Jev's confidence clearly separated right from wrong answers. Clef's barely did.
- **Jev is closed.** It's a paid API. Clef is the open alternative.
- **It's new.** One reviewer's advice: "Do not put it in production this quarter" ([wavect.io](https://wavect.io/blog/jev-ai-decision-model-review/?ref=airabbit.blog)).

## The Bottom Line

Decision models aren't a smarter chatbot. They're the opposite: an AI that's not allowed to talk.

And that's exactly why they're fast, cheap and predictable.

If you want to go deeper, I compared [Jev against Cloudflare's Clef models](https://airabbit.blog/cloudflare-just-shipped-two-decision-models-i-raced-them-against-jev/) with real numbers, and wrote about [why Stripe wants OpenRouter](https://airabbit.blog/what-stripe-sees-in-openrouter-that-most-miss/).

## Reference: Your First Decision Call

From [OpenRouter's Jev tutorial](https://openrouter.ai/docs/guides/community/jev-tutorial?ref=airabbit.blog). Replace the ticket with your own problem:

```

curl https://openrouter.ai/api/alpha/decisions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "typesafe/jev-1.13",
    "state": {
      "ticket": "My checkout page shows a blank screen after I click Pay."
    },
    "questions": {
      "is_bug": {
        "type": "noul",
        "instructions": "Is the customer reporting a software defect?",
        "criteria": {
          "true": "The customer describes broken or unexpected product behavior.",
          "false": "The customer is asking a question or requesting a feature."
        }
      },
      "team": {
        "type": "choice",
        "instructions": "Which team should own this ticket?",
        "criteria": {
          "payments": "Checkout, billing, or payment processing issues.",
          "frontend": "Rendering, layout, or browser compatibility issues.",
          "account": "Login, permissions, or profile issues."
        }
      }
    }
  }'

```

You get back a probability for "is it a bug" and a pick for the team, with a probability for each option.

To turn your own problem into a decision:

- write down the question you keep asking an AI
- list every possible answer
- describe each answer in one line
- send the situation as the `state`

Happy deciding.