Two models · One Jev AI account

Laya models on Jev AI

Give Laya a short text and a typed question. Get a yes/no probability, a category or a score. Choose English or Multilingual in the playground, then use the same model through the Jev AI API.

Try Laya English Create API key Copy API request Try native Jev

Try it on this page

Run Laya English right here

Edit the example or paste your own text, then run it. Sign in to run: new accounts get 20 welcome credits, and a failed run costs nothing.

Open the full playground

Run with

Content moderation · Laya English

1 Input

lol nobody asked for your opinion. people like you should just log off forever, seriously go touch grass and stop posting trash here

2 Questions

Choice Which label best describes this comment?
Yes / No Should a human moderator review this comment before it stays visible?
Score How severe is the harm in this comment?

Laya English

Beta · English short-text decisions

512 total tokens per question, including text, instructions, labels and framing.

laya-english

Checking connection…

Open in playground

Laya Multilingual

Beta · Short-text decisions across languages

1,024 total tokens per question, including text, instructions, labels and framing.

laya-multilingual

Checking connection…

Open in playground

Use Laya with your Jev API key

Create a key on the Jev API page and store it as JEV_AI_API_KEY on your server. Both models use POST /api/v1/systemone. First check authenticated GET /api/v1/models for availability.

curl --fail-with-body https://jev-ai.pro/api/v1/systemone \
  -H "Authorization: Bearer $JEV_AI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "laya-english",
  "state": "My payment failed. Please help.",
  "questions": {
    "billing": {
      "type": "noul",
      "instructions": "Is this message about billing?"
    }
  }
}'

Read answers.billing.noul for the probability of yes. You can also use choice, score or a saved judgeId. Full Laya API reference →

Input limits and billing

Each label has a 48-token limit. Additional question-and-label budgets apply. Oversized input returns 422 without a charge; it is never silently truncated.
Input usage counts each question's sequence, including repeated text. Laya reports zero output tokens.
On Jev AI, both Laya models use a 2× rate: actual input tokens × 2, or 2 credits for the whole request when tokens are insufficient. Failed requests are not charged.
An unconnected model returns 503 before credits are reserved. Check availability before running a batch.

View API pricing Set up with your coding agent Compare Jev and Laya