TypeSafe (Jev)

TypeSafe’s Jev models return a typed judgment — a probability, a choice, or a score — instead of generated text. The AI Gateway routes these calls through /v1/decisions, a separate endpoint from chat completions, while still giving you the gateway’s full feature set: authentication, routing, retries, circuit breaking, caching, logging, and cost tracking.

/v1/decisions does not support streaming. Only before-request guardrails apply, scanning the state field only.

Add Provider in Model Catalog

Go to Model Catalog → Add Provider.
Select TypeSafe.
Enter your TypeSafe API key.
Name your provider (e.g., typesafe).

Complete Setup Guide

See all setup options and detailed configuration instructions

Quick Start

cURL

curl https://aigw.portkey.ai/v1/decisions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $PORTKEY_API_KEY" \
  -H "x-portkey-provider: typesafe" \
  -d '{
    "model": "jev-latest",
    "state": "Help! My payouts have been failing for 3 days.",
    "questions": {
      "department": {
        "type": "choice",
        "instructions": "Which team should handle this?",
        "criteria": { "billing": "Payments", "technical": "Bugs" }
      }
    }
  }'

Response:

{
  "model": "jev-1.13.0",
  "answers": {
    "department": {
      "type": "choice",
      "choice": "billing",
      "probabilities": { "billing": 0.88, "technical": 0.12 },
      "confidence": 0.81
    }
  },
  "usage": { "input_tokens": 296, "output_tokens": 20 },
  "provider": "typesafe"
}

Question Types

Each entry in questions picks a type, which determines the shape of its answer:

Type	Use for	Answer shape
`noul`	A yes/no-style judgment	`{ noul: <0–1 probability> }`
`choice`	Picking one label from a fixed set	`{ choice, probabilities, confidence }`
`score`	A graded position on a scale	`{ score, legend, probabilities, confidence }`

criteria on a question defines the type-specific detail — for a choice question, the set of labels to choose from.

Model

model defaults to jev-latest if omitted. Pin a specific version (e.g. jev-1.13.0) for reproducible judgments across a TypeSafe model upgrade.

Pricing

TypeSafe bills on input tokens only — output tokens (the typed judgment itself) are free. Usage is reported in the response’s usage.input_tokens / usage.output_tokens.

Next Steps

Guardrails for Decisions

Scan state before it reaches the model

Gateway Configs

Add retries, fallbacks, and caching

Observability

Monitor and trace your decisions requests

Integrations

LLM Integrations

Cloud Platforms

Guardrails

Plugins

Vector Databases

Agents

AI Apps

Libraries

Tracing Providers

MCP Clients

MCP Servers

Add Provider in Model Catalog

Complete Setup Guide

Quick Start

Question Types

Model

Pricing

Next Steps

Guardrails for Decisions

Gateway Configs

Observability

​Add Provider in Model Catalog

Complete Setup Guide

​Quick Start

​Question Types

​Model

​Pricing

​Next Steps

Guardrails for Decisions

Gateway Configs

Observability

Add Provider in Model Catalog

Quick Start

Question Types

Model

Pricing

Next Steps