Skip to main content
JevModel

JevModel

Typed decision API for support triage, moderation, chatbot routing, scoring, and agent gates. Each call returns structured JSON.

Freemium·API·AI·Moderation·Routing·AI Agents·Developer Tools
JevModel preview 1

What is JevModel?

JevModel is a typed decision API at jevmodel.io. You give it one shared state, then ask yes/no, choice, or score questions, and each call returns structured JSON your application can route, log, and execute. The site positions it for support triage, content moderation, chatbot intent routing, lead and risk scoring, and agent gates, such as whether an agent may change billing data, issue a refund, call a tool, or contact a customer.

A request describes the state, asks a narrow question, and defines the decision vocabulary. Example schemas on the site include support triage (normal, priority, or escalate), moderation (approve, block, or review), intent routing (billing, account, product, or sales), and risk (allow, throttle, or review). The playground labels the model jev-1.13, counts questions out of 8, and posts to jevmodel.io/api/v1/decisions.

The homepage says it is free to start, with no signup, and the playground gives 10 anonymous trials. More trials, API keys, and credit packs require a Google login. Sign in, open Settings, create an API key, buy credits, and call the decisions endpoint.

Each decision call uses 1 credit, however many questions it includes, and the response includes the remaining balance. Free use is 1,000 credits a day with no credit card. Paid packs are one-time through Stripe and last 365 days: Starter is $10 for 100,000 credits, Builder is $100 for 1,000,000 credits, and Scale is $1,000 for 11,000,000 credits.

The homepage playground also shows a crossed-out $15, marked 33% off, beside a button that says Start with $10. The site says the user-facing API is the JevModel endpoint, and upstream routing stays internal. Prices are from jevmodel.io and jevmodel.io/pricing, checked October 28, 2026.

Pricing: Free: 1,000 credits a day, no card. Starter $10 for 100,000 credits, Builder $100 for 1,000,000, Scale $1,000 for 11,000,000. One-time packs last 365 days. Checked October 28, 2026.

Features

  • Yes/no, choice, and score questions against one shared state, with several questions in a single call
  • Structured JSON with a decision, confidence, reason, and optional route
  • Support triage, moderation gates, chatbot intent routing, scoring, and agent approval checks
  • Homepage playground with 10 anonymous trials and no signup required to start
  • API keys after Google sign-in, then POST jevmodel.io/api/v1/decisions
  • One-time Stripe credit packs; each decision call uses 1 credit, and paid credits last 365 days

FAQs

Common questions about JevModel

How much does JevModel cost?
Free is $0: 1,000 credits a day, and no credit card is required. Paid packs are one-time and valid for 365 days. Starter is $10 for 100,000 credits, Builder is $100 for 1,000,000 credits, and Scale is $1,000 for 11,000,000 credits. Checkout is Stripe. The homepage playground also shows a crossed-out $15, marked 33% off, beside a button that says Start with $10. Prices are from jevmodel.io/pricing, checked October 28, 2026.
Can I try JevModel without an account?
Yes, for a first look. The homepage says it is free to start, with no signup, and the playground gives 10 anonymous trials. More trials, API keys, and credit packs require a Google login. The free allowance is 1,000 credits a day, with no credit card required.
Is Jev Model a chatbot?
No. The site describes it as a typed decision layer for labels, routes, scores, and workflow gates. A normal language-model answer explains. A Jev response is a compact decision object your product can route, meter, log, and execute.
What does a Jev API response look like?
Every response is structured JSON with a decision label, a confidence score, a reason, and an optional route. Each decision call uses 1 credit, regardless of how many questions it includes. The response includes the remaining credit balance.
How do I get a Jev API key?
Sign in with Google, open Settings, create an API key, buy credits, and call POST /api/v1/decisions on jevmodel.io. The site says the public endpoint is JevModel's own contract, and upstream routing stays internal.
What kinds of decisions can I ask for?
Yes/no, choice, and score. The playground counts questions out of 8, and every question shares one state. Published examples cover support triage (normal, priority, or escalate), moderation (approve, block, or review), intent routing (billing, account, product, or sales), and risk (allow, throttle, or review). You can also ask it to choose a model path, such as a premium model, a fast model, a fallback, or a human review queue.

Ask AI about JevModel

Share

Similar Launches

OpenRouter

OpenRouter

One API for 500+ AI models across 80+ providers — pay with credits that work anywhere, with automatic fallback when a provider goes down.

AgentMail

AgentMail

API-first email for AI agents — give any app or agent its own inbox to send, receive, and reply to emails programmatically.

Ora

Ora

Scan any site or MCP server and get a 0–100 agent-readiness score — can agents find you, access you, use you, and pay you.

Agent Score by Fern

Agent Score by Fern

Check if your documentation is AI-ready — run 22 checks and get a letter grade in seconds.

Claude Code

Claude Code

Anthropic's agentic coding tool — Claude in your terminal, IDE, desktop app and browser, reading and editing your codebase, running commands, opening pull requests and working on tasks in the cloud.

Xirp

Xirp

Spotify's vendor-neutral agentic development environment — run and manage agent sessions across Claude Code, Gemini CLI, and Codex from one place.