Decision model

Jev 1.14.0

Turn context into typed decisions.

Jev 1.14.0 turns shared input into typed results your code can use.

One input. Typed decisions.

Illustrative values · No API call

Shared input

“My subscription was charged twice this month. I can’t update my card, and this is my second message. Please help.”

Pass text or JSON as shared state. Ask several questions in one request; each is evaluated independently against that same input.

Which team should handle this?

Billinghighest-probability option

Billing: 82%
Technical: 13%
Account: 5%

Define a set of categories. The model returns the most likely option and the probability of every option, adding up to 100%.

TypeSafe’s Choice guide ↗

Confidence

Read the whole distribution.

The winning option is only part of the answer. A clear preference and a close call can both select “Billing”. Their distributions show how much ambiguity remains.

TypeSafe’s native Choice and Score answers also include a value derived from the distribution’s shape. It is distinct from an option’s probability and is not a guarantee of correctness.

How TypeSafe defines confidence ↗

Clear preference

Billing: 90%
Technical: 7%
Account: 3%

Close call

Billing: 36%
Technical: 34%
Account: 30%

Illustrative Choice distributions.

Pricing

Catalog pricing

Input / 1M tokens: $0.0462
Output / 1M tokens: Free
Request minimum: $0

Finalized provider inference cost plus 10%. Verified zero-cost requests remain free. Credit holds are temporary; settled charges appear in account activity.

Endpoints

Decision endpoints

OpenAI decision format: POST; Ordered typed questions and answers, including native refusals.
Primary HTTP API: POST; Boolean probabilities, selected choices and rubric scores. Choice and score answers include their full probability distributions.
Native TypeSafe format: POST; Uses Noul for boolean questions. Choice and score answers also return confidence; scores include a level legend.

Limits

Building with Jev 1.14.0

Availability follows the qualified catalog and your API key permissions. If the qualified route is unavailable, requests return 503 before a credit hold or provider call.

Text and JSON in, typed answers out: State can be a string, object or array. This model accepts text input, without audio, images or streaming.
One state, independent questions: Batch up to 64 questions. If a question needs a previous answer, make a separate call. Extra questions still use input tokens.
Your categories and scale: Up to 64 options per choice; 2–10 ordered levels per score. Describe each option clearly, and add an “other” option when categories are not exhaustive.
32 KiB normalized request limit: The upstream JSON must fit within 32,768 UTF-8 bytes, including routing fields MiniRouter adds.

Example

HTTP example

Use an explicit model and an integration API key. Disable automatic retries: a lost response may still incur cost.

Decision HTTP request

curl --fail-with-body https://api.minirouter.sh/v1/evaluate \
  -H "Authorization: Bearer $MINIROUTER_API_KEY" \
  -H 'Content-Type: application/json' \
  --data '{
  "model": "typesafe-ai/jev-1.14.0",
  "state": "The subscription was charged twice.",
  "questions": {
    "billing": {
      "type": "boolean",
      "instructions": "Does this describe a billing problem?"
    }
  }
}'

Every model, one key.

Get an API key Read the docs