Roar AI
Get started
All models
TypeSafe AI · Evaluation

Jev API in Australia

A judge model: typed answers about your data, each with a probability, in well under a second. Priced in Australian dollars for teams in Australia, on the same key as every other model.

InputA$0.0636per 1M tokens
OutputFreeper 1M tokens
BillingOne bill, in AUDwith every other model

Jev API pricing in Australia

InputA$0.0636 per 1M tokens · $0.0433
OutputFree per 1M tokens · Free

In Australian dollars, the currency your card is charged in, with the published US dollar rate beside each.

For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost A$0.1908 — 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.

Prices are our published US dollar rates converted at A$1.47 to the dollar, our rate for October — the same rate your card is charged.

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.

What is Jev good for?

  • 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.

Specs

Made byTypeSafe AI
ReleasedSeptember 2026
TypeEvaluation
Context window64K tokens
ReadsText
WeightsClosed
Processed inGlobal
Model idjev

Using Jev from Australia

Roar AI provides access to Jev through the Roar AI gateway, charged in Australian dollars on one bill with every other model. Requests from Australia go through our gateway in Singapore today; a gateway in Sydney is coming. Developers can use Jev alongside other supported models without a separate integration for every provider.

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": {…}}'

Where is Jev processed?

Requests to Jev are processed on international infrastructure, outside Australia. The model directory says where each model is processed.

Questions

How much does Jev cost in Australia?

Input is A$0.0636 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 A$0.1908. Prices are our published US dollar rates converted at A$1.47 to the dollar, our rate for October — the same rate your card is charged. The rate is published and does not change from one request to the next.

Is Jev open source?

No. TypeSafe AI does not publish the weights, so it is only available through an API like this one.

Try Jev
on one key

Sign up, get a key and call it with the SDK you already use. Pay in your local currency, on one bill.