jevmodel.org account

Sign in for 100,000 free input tokens

About 500 Jev requests in the playground or from your own code with an API key. Packs start at $9.90 when you need more. No card required.

By signing in you agree to our terms. We only use your email for your account.
Jev Model · Retrieval & knowledge

Live Web Context

Let live evidence change the answer.

A model's training data goes stale the day it ships. Search for the evidence yourself, hand Jev the snippets and the claim, and get a typed verdict grounded in what is true today — not what was true at training time.

One statefocused questions
  • Claim or questionThe yes/no proposition to verify
  • Search resultsSnippets, dates and sources you fetched
  • As-of dateWhen the evidence was collected
Structured answersfor your application
  • Evidence verdictsupported · contradicted · insufficient
  • Answer probabilitynoul: P(yes) for the claim
  • Evidence qualityscore: how strong the sources are

Try it with your own rules

Start from the preset below, adapt the questions, and inspect the typed answers. Run it live in the playground — it is the same request shape your application will send.

ChoiceDo the supplied sources support the claim as written?
Yes / NoIs the claim true as literally stated?
ScoreHow strong and current is the supplied evidence?
Open in playground

What Jev returns

Illustrative output for the preset below — run it live to get real values for your input.

claim

The EU AI Act applies to open-source models

evidence

eur-lex.europa.eu: "…does not apply to AI systems released under free and open-source licences…" (2024-07-12) · openai.com/blog: "GPAI provisions do cover open weights above thresholds" (2025-08-01)

From one example to a reusable workflow

01

Fetch first, decide second

Your code owns retrieval — pull snippets from your search provider and serialize them with dates and sources into the state.

02

Separate evidence from answer

Ask whether the sources support the claim (choice) and whether the claim is true (noul) as different questions — strong evidence for a false claim is a real outcome.

03

Score the source quality

An evidence-quality score tells you whether a surprising verdict is grounded in a primary source or a stray blog post.

Keep the criteria separate

CheckWhat it measuresHow to use it
Verdict · ChoiceDo the supplied sources support the claim?supported / contradicted / partial keeps "the evidence is mixed" distinct from "no evidence".
Answer · Yes/NoIs the claim true given this evidence?The noul probability is your fact-check signal — threshold it per how costly a wrong yes is.
Evidence quality · ScoreAre the sources primary, recent and independent?Down-weight verdicts built on weak evidence instead of treating all snippets equally.
01

Grounding is a decision problem

The hard part of live context is not fetching — it is deciding whether what you fetched actually answers the question. That judgment is exactly what a typed decision returns.

02

Dates are part of the evidence

Include source dates in the state and say in the instructions how to weigh them. A 2024 regulation page and a 2026 changelog disagree because the world changed — let the instructions say which wins.

03

Compose with RAG evaluation

Web context checks claims against evidence; RAG evaluation gates which evidence enters the context at all. Use both when your pipeline retrieves from the open web.

FAQ

Does Jev browse the web itself?

No — on jevmodel.org you supply the snippets. Fetch with your search provider, pass results as state, and Jev weighs them.

How much evidence fits?

State is limited to 8,000 characters serialized — roughly 10–20 focused snippets with sources and dates.

Is the verdict reproducible?

The same state gives similar probabilities, but evidence changes. Log inputs with timestamps so a verdict stays explainable later.

API keys

Call Jev with your key.

Send state plus typed questions to the local Jev endpoint. Successful requests charge input tokens. Add an Idempotency-Key header when retrying.

+ New key