Typesafe AI

Typesafe AI serves System One models. Instead of a chat conversation, a System One request sends a state and a set of typed questions. The response returns a typed answer for each question, with a calibrated probability. Typesafe AI only supports System One requests at https://gateway.ngrok.ai/v1/systemone. Chat Completions, Responses, and Messages requests don’t reach Typesafe AI models.

Typesafe AI is a built-in provider you can pay for with credits, so a provider key is optional. Add your own Typesafe AI key to bill usage to your Typesafe AI account instead of your ngrok.ai credits.

Setup

Create an access key and add credits

Follow the quickstart to create an access key and purchase credits in app.ngrok.ai.

Store your Typesafe AI API key (optional)

Skip this step to pay with credits. To bring your own key, create an API key in your Typesafe AI account. Then add a provider key and create an access key configuration with a typesafeai routing rule that uses it.

Send requests

Send a POST request to /v1/systemone with your access key:

curl https://gateway.ngrok.ai/v1/systemone \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ng-xxxxx-g1-xxxxx" \
  -d '{
    "model": "jev-latest",
    "state": "Customer: My order arrived broken and I want a refund today.",
    "questions": {
      "urgency": {
        "type": "score",
        "instructions": "How urgent is this message?",
        "criteria": [
          "Not urgent: no action needed.",
          "Somewhat urgent: handle within a few days.",
          "Urgent: handle today."
        ]
      }
    }
  }'

Request format

A System One request body has three fields:

Field	Description
`model`	The model ID, such as `jev-latest`.
`state`	The text the model evaluates.
`questions`	An object that maps each question ID to a typed question. It must contain at least one question.

The gateway removes any other top-level field before it forwards the request. System One doesn’t stream, so a request with "stream": true returns an error. See the Typesafe AI API reference for question types and the response format.

Available models

See the model catalog. jev-latest points at the current Jev build, and jev-preview points at the next one.

Next steps

Typed-question APIs: How System One requests work
Provider keys
Access key configurations

Concepts

Getting Started With

SDKs

Agents

Guides

Observability

Examples

Reference

API Reference

Setup

Request format

Available models

Next steps

​Setup

​Request format

​Available models

​Next steps

Setup

Request format

Available models

Next steps