OpenJev: a small model that answers questions instead of writing
Give it some text and a question with a fixed answer space. It returns the answer, typed, with a number beside it. It does not write, and there is no field in the response where it could. We run it on our own hardware and it is free to call.
OpenJev is not Jev
This is the first thing to settle, because the names invite the opposite conclusion. Jev is TypeSafe's model. OpenJev is an independent open-source model, MIT licensed, published by AlexWortega. They are not the same model, not the same people, and OpenJev is not a smaller or free tier of Jev. It answers a similar shape of question, and that is the extent of it.
We do not sell or resell Jev. We host OpenJev and give it away, and we expect it to be materially weaker than Jev. We have not benchmarked the two against each other and no published comparison exists, so we are not going to put a number on the gap — see the full comparison for what can and cannot honestly be said.
What it is, technically
| Architecture | A natural-language-inference cross-encoder built on a Qwen3.5 4B base |
| What it outputs | For a premise and a hypothesis: how strongly the premise entails it |
| Licence | MIT |
| Author | AlexWortega, published on Hugging Face |
| Input we accept | Text and JSON. The v2 checkpoint also reads images; our endpoint does not expose that yet |
| Where we run it | Our own GPU, scaled to zero between calls |
The three question types we expose — a yes/no, a labelled choice, a score over rungs you name — are all the same operation underneath. Your text is the premise, your question is the hypothesis, and the answer is the entailment between them.
How good is it? What its authors publish
These are the model authors' own figures, from the Hugging Face card, read on 2026-09-20. We have not re-run them, and they are zero-shot scores on standard natural-language-inference sets — the task underneath all three question types, and not your task.
| Benchmark | v1 | v2 (what we serve) |
|---|---|---|
| ANLI r3 (adversarial NLI) | 0.42 | 0.63 |
| WANLI | 0.63 | 0.77 |
| MNLI | 0.91 | 0.91 |
A benchmark score is not a promise about your data. The only number that should decide anything is the one you get running your own labelled examples through it, which costs nothing here.
The one thing to understand before you set a threshold
For a labelled choice, every option is scored against your text and the scores are then divided by their total so they sum to one. That step throws away how strong the scores were.
Three options the model supports equally weakly come back as an even split. Two options it supports equally strongly come back as an even split too. Opposite situations, identical response.
So the number is a share of the agreement found, not the probability the answer is correct. Read it as an ordering with a margin — wide means the model preferred one option clearly, narrow means it did not — and set your threshold from your own examples rather than from the number's face value. The API reference works the arithmetic through.
Calling it
One POST, a key from user.blockrun.ai, no payment header and no wallet.
curl -X POST https://api.blockrun.ai/v1/decide \
-H "authorization: Bearer $BLOCKRUN_API_KEY" \
-H "content-type: application/json" \
-d '{"state": "Help! My payouts have been failing for 3 days.",
"questions": {"urgent": {"type": "noul",
"instructions": "Does this convey urgency?"}}}'Full request shape, all three question types and the response fields are in the API reference. The endpoint itself is described on the Decide page.
OpenJev questions: what it is, licence, accuracy, how to call it
- What is OpenJev?
- An open-source natural-language-inference cross-encoder built on a Qwen3.5 four-billion-parameter base, published under MIT by AlexWortega. It answers typed questions about a piece of text rather than writing anything.
- Is OpenJev the same as Jev?
- No. Jev is TypeSafe's model. OpenJev is an unrelated open-source model that took a similar name because it answers a similar shape of question. It is not a smaller checkpoint, a free tier, or a community port of Jev, and we do not resell Jev.
- What licence is the OpenJev model under?
- MIT, which is why we can host it and give the calls away. The weights are public on Hugging Face if you would rather run it yourself.
- How accurate is OpenJev?
- Its authors publish zero-shot scores on standard natural-language-inference sets and we link them with the date we read them, but we have not re-run them and none of them is a comparison against Jev. A benchmark is not a promise about your data — run your own labelled examples, which costs nothing here.
- How do I call the OpenJev API?
- One POST to the decide endpoint with a bearer key from user.blockrun.ai. No payment header and no wallet: it is free with any registered key. The API reference carries the request shape and every response field.
- Does OpenJev accept images?
- The v2 checkpoint reads images as well as text, but our endpoint does not expose that yet — we accept text and JSON. If you need the image path today, run the weights yourself.
- OpenJev vs a chat model with a JSON schema?
- A chat model can be prompted into a label, but you pay per token, tune a prompt, police a schema and get a string with no calibrated number behind it. This returns the type and a margin directly, free. The honest move is to try both on your own data — one key reaches both here.
- Why is calling the OpenJev API free?
- A judgment costs less to serve than the smallest amount our paid rail can settle, so metering it would cost more than the answer does. It is free behind a registered key instead.
- Can an AI agent use OpenJev on its own key?
- Yes. Give the agent a registered key and it decides as often as it needs to within a generous hourly limit, getting back a value it can branch on without a parser.