Roar AI
DiscordGet started
All models
TypeSafe AI · Evaluation

Jev

Jev costs $0.042 per million input tokens and Free per million output tokens on Roar AI. A judge model: typed answers about your data, each with a probability, in well under a second.

Input$0.042per 1M tokens
OutputFreeper 1M tokens
Context window64Ktokens

Jev API pricing

Input$0.042 per 1M tokens
OutputFree per 1M tokens

Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $0.13. Every rate is published and stays the same from one request to the next. See every model.

Rates as of 20 November 2026.

Specs

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

Is Jev worth the price?

If you are using a large model as a judge, it is worth testing. Jev answers typed questions, such as picking an option or scoring against a rubric, typically in 70 to 500 milliseconds, and only the input is billed. That suits grading other models’ output, guardrail checks, triage and routing.

It does not write text, so it cannot replace a chat model. TypeSafe lists maths and counting, comparing dates, multi-step logic and double negatives among its weak spots, and its probabilities are not guaranteed to be consistent, so check a sample of its verdicts before you rely on them.

Jev and the models to compare it with, priced per 1M tokens
ModelInputOutputChoose it for
Jev$0.042FreeGrading and guardrail checks.
GPT-6 Luna$0.10$0.50Sorting and routing when you also want written answers.
DeepSeek-V4.1-Flash$0.195$0.78A low-cost chat model for coding and tool use.

Prices per 1M tokens.

About Jev

Jev is not a chat model and does not write text. You give it some state (a conversation, a document or 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.

Jev limitations

  • TypeSafe lists its own weak spots: maths and counting, comparing dates, multi-step logic, double negatives and text written to mislead it.
  • Its probabilities are useful but not guaranteed to be consistent.
  • English is its strongest language; others work at lower accuracy.

How to use the Jev API

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": {…}}'

Jev FAQ

How much does Jev cost?

Input is $0.042 per 1M tokens; output is Free per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $0.13.

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 only means changing the model name 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.

What is the context window of Jev?

Jev can read up to 64K tokens in one request.

Start using Jev

Create a free account, get an API key and call Jev with the OpenAI SDK.