Decision Models Explained: Jev, Clef, Laya and the Alternatives

October 2, 2026, updated October 15 / Arvid Andersson

A decision model answers your code's question with a probability for each possible answer. Jev made the idea popular in September 2026. Within three weeks there were open-weight alternatives (Laya, Kev), open-weight models from Cloudflare (Clef) and Perplexity (pplx-decider), EU hosting (System1 Models) and a preview from OpenAI. They are fast and cheap enough to sit inside a loop. They are not a replacement for an LLM.

What a decision model is

Most of what an application asks an LLM is not a request for prose. Is this ticket about billing? Should the agent call the search tool or the database tool? Is this message urgent? The answer is one of a few options. An LLM still produces it the way it produces everything else: token by token, as text your code then has to parse and trust.

A decision model skips the text. You send it a state (a message, a document, some JSON) and a set of typed questions. It returns an answer per question, with a probability for every allowed option:

• Choice: pick one option from a list you define.
• Score: rate something on levels you define.
• Yes/no: the probability that the answer is yes. TypeSafe calls this a "noul".

Because nothing is generated, all questions are answered in one pass. Pricing reflects that: Jev charges for input tokens only; output is free.

What it looks like in practice

In a test on 2 October 2026, Jev received a customer message ("I was charged twice for my October invoice and need the duplicate refunded before Friday") with three questions in one request: which team should handle it, whether it needs a reply within 48 hours and how frustrated the customer is on a four-level scale.

It answered billing with probability 1.0, urgent at 0.73 and frustration at 1.19 out of 3 (most weight on "mildly annoyed"). Eight requests took 0.22 to 0.28 seconds each from Sweden, network included. The request used 429 input tokens, which at Jev's listed $0.042 per million comes to about $0.00002.

At that price and speed you can ask on every incoming message or agent step.

For a hands-on look, five of them were tested as the first reader in front of an AI agent's inbox, on 16 emails in English and Swedish: Jev, Laya, Strom and System1 tested.

The options, as of October 2026

This table compares the first seven options on how you run them. Every decision model with its current hosts and verified prices is on the decision models page.

Prices and specs checked against each provider's own pages, 2 October 2026; the Laya hosts on 3 October; OpenAI, pplx-decider and Decision Models on 15 October. See all Jev alternatives in the directory.

What the table doesn't show:

• Laya works best fine-tuned. Its own benchmark shows accuracy going from 0.362 zero-shot to 0.766 after fine-tuning on the task. The English checkpoint reads 512 tokens; the multilingual one handles 100+ languages and up to 8,192 tokens if you raise the limit.
• Kev and Clef speak Jev's API. You can point TypeSafe's SDK at them, which makes switching cheap. Kev's README reports its own benchmark scores against Jev; Cloudflare reports its own for Clef. Both are self-reported; test on your own data before relying on them.
• pplx-decider reads the most at once. Perplexity's model takes up to 262K input tokens per request, images included, at $0.02 per million input tokens, about half what Jev charges. Perplexity reports 85.7% across 11 benchmarks against 84.5% for Jev, measured through its own API. Like the other scores here, that is self-reported.
• You can run them like Ollama. Ollaya pulls Laya, Kev, Clef and other decision models by name and serves them locally on Jev's endpoint, on CPU or GPU.
• OpenAI's version is a different design. Its Decisions API, announced at DevDay (29 September 2026) and now in public beta, uses gpt-6-luna, a general-purpose model, to choose from predefined answers. At $0.10 per million input tokens it costs more than twice what Jev does. OpenAI has not said whether its probabilities are calibrated, which is the property the purpose-built models are trained for.
• EU options exist. Decision Models (decisionmodels.io, formerly System1 Models) runs an EU-only tier on contracted EU operators with a DPA. Berget AI hosts Laya in Sweden. OpenAI offers European data residency on its Decisions API for eligible customers. See the European AI providers list for more.

What people build with them

A community list of open-source Jev projects (awesome-jev-projects) keeps showing one pattern: the decision model sits inside a loop and makes the small calls a bigger model would be slow and expensive for.

• Routing: decide which model, team or handler gets a request. See AI gateways explained for the gateway side of this.
• Context pruning: score old tool output and drop what no longer matters before the next agent turn.
• Guards: check input and output for policy problems before they reach a user. The guardrails comparison covers the dedicated tools.
• Agent referees: judge whether an agent's "done" is backed by test output, before anyone trusts it.
• Re-ranking and filtering: score retrieved passages or dataset rows, then let code decide what to keep.

When not to use one

• You need text. Decision models choose; they don't write. Pair one with an LLM rather than replacing it.
• You have labelled data and one fixed task. A small model fine-tuned for that task can beat a general decision model. It also runs anywhere. indecis (MIT, Go) is one library for training tiny ones that run on a CPU.
• Your input is long. Context limits range from 512 tokens to about 262K (pplx-decider). Check the model card for how accuracy holds up at your document length.
• Structured output from your current LLM is good enough. If you already call an LLM with a JSON schema and the latency and cost are fine, adding another model is extra moving parts. If that is where you are, there is no reason to switch yet.

FAQ