Skip to main content

Jev is now available on ngrok.ai

Jev by Typesafe AI is now available on ngrok.ai.

Unlike a chat model, Jev is a System One model built to make decisions rather than write prose. Send it some state and a set of typed questions, and it returns a typed answer and calibrated probability for each one. That means less parsing, validation, and retry logic when all you need from a model is a decision.

Send requests to:

https://gateway.ngrok.ai/v1/systemone

Authenticate with your ngrok access key and pass state, model, and questions in the request body. Any other fields are removed before the request is sent to Typesafe AI.

Usage is billed directly to your ngrok credits, so you don’t need a Typesafe AI account or API key. Input costs $0.042 per million tokens, and output is free.

Available models:

  • jev-1.13.0
  • jev-latest → currently jev-1.13.0
  • jev-preview → currently jev-1.13.0

The System One endpoint does not support streaming or tools.

Get started

  1. Open Models and filter by provider:typesafeai.
  2. Create an access key that allows Typesafe AI, and confirm your account has credits.
  3. POST a state and your questions to https://gateway.ngrok.ai/v1/systemone with "model": "jev-latest".