JOpenRouter
Jev 1.14
typesafe/jev-1.14
TypeSafe decision model released October 14, 2026, for typed classification and routing.
AI-JEV · SUPPORT TRIAGE, MODERATION, ROUTING
One Decisions API for Jev and 18 decision models
Run Jev 1.14, GPT-6 Luna Decisions, Clef, Mercury Decide, and other decision models through one API. Get typed answers with probabilities for the next step in your workflow.
100 welcome creditsSupport · moderation · routingTyped answers with probabilities
SAMPLE DECISIONjev-1.14
“I was charged twice for the same order and need the duplicate payment refunded.”
Is this request urgent?Yes94% confidence
Which team should handle this?Billing91% confidence
Typed answers, ready to route→
18 AVAILABLE MODELS · 19 LISTED
Browse models →Choose the model for the work.
JOpenRouter
Jev 1.13
typesafe/jev-1.13
Typed decisions for production classification and routing.
SOpenRouter
Solar Decide
upstage/solar-decide
Decision model for classification and scoring tasks.
TRY A DECISION
Run the same question in Playground.
Choose a model, edit questions, and inspect typed answers before connecting your workflow.
Open the interactive Playground →ONE API · MULTIPLE PROVIDERS
From a test to your product.
Use the same typed questions in your app with one server-side API key. Select models, compare answers, and scale with Batch.
cURL · POST /api/v1/systemone
curl https://ai-jev.pro/api/v1/systemone \
-H "Authorization: Bearer $JEV_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"typesafe/jev-1.14","state":"...","questions":{"urgent":{"type":"noul","instructions":"Is this urgent?"}}}'Read API docs →SIMPLE CREDIT PRICING
Pricing details →Pay for the decisions you run.
For trying a few models
100,000 credits
Never expires. Shared across Playground, API, and Batch.
For production workflows
1,000,000 credits
Never expires. Shared across Playground, API, and Batch.
For higher volume
10,000,000 credits
Never expires. Shared across Playground, API, and Batch.
Compare per-model input-token prices and official references on the pricing page.
WHAT CAN JEV HELP WITH?
Give every message a clear next step.
Choose an answer space once, then route, review, or score each request with structured output.
01
Flag for review
Check whether a message needs a person to take a closer look.
02
Choose a queue
Send a ticket or lead to the team or category you define.
03
Set priority
Score urgency, fit, or quality against your own labels.
Questions before you start?
What is AI-Jev?
Jev turns a shared text or JSON state into typed Yes/No, Choice, and Score answers for workflows such as support triage, moderation, routing, and lead qualification.
Which models can I use?
Compare 19 listed models, including 18 available routes. Model IDs and input-token credit rates are listed in the model directory.
Can I ask more than one question?
Yes. A request can include up to 8 named questions. Span models accept Noul yes/no questions only.
How does billing work?
Input tokens are charged at the selected model rate. Output tokens are free. New AI-Jev accounts receive 100 welcome credits; top-up packs do not expire.
Can I classify images?
Vision models accept up to four PNG, JPEG, or WebP images, up to 4 MiB each and 8 MiB total. Check each model's image support before running.
Does AI-Jev save the text I submit?
Completed run content is not saved to an account history. Saved configurations and credit or billing records are stored. The model provider's handling terms apply; see the Privacy Policy.
RESOURCES
All resources →Move from a test to production.
QUICKSTART
Make your first API call
Use your Jev API key to run a typed decision from your server.
Read quickstart →BATCHProcess a file of decisions
Apply the same questions to a collection of rows and export results.
Open Batch →USE CASESupport ticket triage
Route tickets, set priority, and flag cases for human review.
Explore use case →TRY IT WITH A TICKET
Open Playground →