Jev
A judge model: typed answers about your data, each with a probability, in well under a second.
About Jev
Jev is not a chat model and does not write text. You give it some state — a conversation, a document, another model’s answer — and typed questions: pick one of these options, score this against a rubric, or how likely is this statement to be true. It answers all of them at once, each with a probability, typically in 70 to 500 milliseconds.
That makes it a fast, cheap replacement for using a large model as a judge: grading other models’ output, guardrail checks, triage and routing. Tools such as deepeval and Arize already use it that way, and only the input is billed. It comes from TypeSafe AI, founded by Diogo Almeida, formerly of OpenAI.
Where it’s strong
Grading the output of other models.
Guardrail checks before or after a larger model.
Ticket triage, intent detection and routing.
Moderation, with a confidence score to decide when to escalate to a person.
Where to be careful
TypeSafe lists its own weak spots: maths and counting, comparing dates, multi-step logic, double negatives and text written to mislead it.
Confident is not the same as right — its probabilities are useful, not guaranteed consistent.
English is its strongest language; others work at lower accuracy.
Price
For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost $0.14 — a long prompt and a page of answer each. Every rate is published and stays the same from one request to the next. See every model.
Specs
jevCall it
Send the state to judge and the questions to answer; typed answers come back. Read the docs.
curl https://api.roar-ai.com/v1/evaluate \
-H "Authorization: Bearer roar_live_…" \
-d '{"model": "jev", "state": "…", "questions": {…}}'Questions
How much does Jev cost?
Input is $0.0483 per 1M tokens; output is Free per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost $0.14. The rate is published and does not change from one request to the next.
Can I use Jev alongside other models?
Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from Jev to another model is a change to one word in your code.
Is Jev open source?
No. TypeSafe AI does not publish the weights, so it is only available through an API like this one.