Jev playground: test your own decision rules.
Jev is TypeSafe’s model for focused decisions. Try classifying a message, compare the allowed outcomes, and see where human review belongs.
Your decision
Illustrative sample — not a live model response.
Run a decision or open the labeled sample to see the result here.
A high score is not a guarantee. Keep a person in control of consequential actions.
API docs →How to test a decision in the Jev playground
Choose one question and clear labels
Start with a support ticket, sales lead or product comment. Replace the sample with an anonymized message, explain the decision in the instructions, and choose distinct labels. A useful label names the next queue or action; overlapping labels make the result harder to evaluate.
Compare the sample with a live run
The labeled sample shows the response format only; it is not a prediction for the message you edited. Run the decision explicitly to request a live result, subject to trial limits and service availability. Loading a preset does not run or charge a decision.
Inspect uncertainty before automating
Read the selected choice together with confidence and needsReview. Missing confidence or a result below your threshold needs review. A high score is not a guarantee: test ambiguous and mixed messages against examples your team has labeled, then connect the API only when the errors are acceptable for your workflow.
Jev API →Questions before your first decision
Is this the official Jev website?
No. Jev API Pro is an independent workspace. Jev is a model from TypeSafe, accessed here through OpenRouter.
Can I try it without an account?
Yes, when live decisions are available: one trial attempt per source address per UTC day, subject to shared trial capacity. A labeled example is also available.
What happens when the model fails?
We show an explicit error. Failed account decisions are refunded, and we do not substitute a different model silently.
Do you store the messages I submit?
Decision history stores the result, request hash, and operational metadata, not the submitted message. Your text is sent to OpenRouter and its model provider for inference.
What does a credit buy?
One completed classification within the published input limits uses one credit. Signed-in accounts receive 20 signup credits and can claim two daily check-in credits.
Can I automate business actions?
Use the API to get decisions. Your own application checks permissions and performs actions. Low-confidence or missing-confidence results should go to review.