Skip to main content

Jev 1.14 API

typesafe/jev-1.14/decision

TypeSafe’s Jev 1.14 decision endpoint classifies and scores text or JSON with up to 64 named questions. It returns typed probabilities, options and scores for routing and review workflows.

From $0.0000504/1,000 tokens

Workbench

Input

Decision
Name up to 64 questions and give each a type and instructions; use criteria for 1–255 choice options or 2–10 score levels arranged from low to high, with optional true/false descriptions for noul. Keep state plus each question within 32k tokens and the combined request within 64k.
Supply a string, JSON object or array containing the evidence for every judgment; questions cannot rely on another question’s answer. For a video-related check, include its transcript, on-screen text or frame descriptions instead of a media file. at least 1 characters
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
Example result
  • hookChoice

    problem

    Confidence 100%

  • proofScore

    1.44

    Level 1 · Some proof, such as a single statement or quick shot

    Confidence 28%

  • has_offerYes / no

    98% chance of yes

537 input tokens

Missing the model you need?

Turn a transcript, ticket or review into typed judgments that your application can route, rank and check.

Key numbers

Questions per call
64
Request token ceiling
64k
Supported answer types
3
Earlier 3-question probe
0.62 s
425 input tokens in that measured call

Token budget

Input window
65,536
tokens in one request

Before you spend

Decision
  • This decision endpoint permits up to 64 questions and 64k tokens per request; state plus any individual question must fit within 32k tokens. Choice accepts 1–255 options and score accepts 2–10 levels. Supply text or JSON rather than image, video or audio files; box questions are not offered here.
  • Jev returns no reasoning text, and a typed answer can still be incorrect. Choice and score include confidence and probability distributions; noul supplies a yes probability from 0–1. Use uncertain judgments for escalation rather than treating them as verified facts.

What it does

Typed output

A probability, a category or a rubric

Select among 3 question types to match the value your code needs. Noul returns a yes probability from 0–1; choice returns a named option with confidence and option probabilities; score returns a probability-weighted level with confidence, a legend and level probabilities.

Parallel questions

One state, independent judgments

Up to 64 questions evaluate the same state independently and in parallel, with little latency change as questions are added. Ask about a ticket’s team, urgency and refund intent together, then combine those answers in application logic.

Measured examples

Inspect uncertainty beside the answer

Our short-video review returned a proof score of 1.44 with confidence 0.28, while its offer probability was 0.98. Those values describe different judgments: a clear offer does not make the evidence for a product claim equally clear.

Workflow control

Keep escalation in your code

Define the probability and confidence thresholds that send an item to a person or a generative model. Jev 1.14 supplies structured judgments without a written rationale, so review the original evidence when an uncertain answer affects the next action.

Where it fits

  • Screen short-video advertising copy

    Provide a product-clip transcript, on-screen text and frame descriptions as state, then ask about hook style, proof and an offer. Our shown example returned problem as the hook, proof 1.44 and an offer probability of 0.98; it used 537 input tokens.

  • Route a billing support ticket

    Submit a message such as “I was charged after cancelling; please refund the renewal” with relevant account metadata. Request team, urgency and refund intent; our support example returned billing, urgency 1.6 and refund_requested 0.96 across 422 input tokens.

  • Separate review sentiment from intent

    Use a review such as “The finish chipped, but I would order again if that is fixed” to ask separate sentiment, issue and return-intent questions. Our review example produced sentiment 1.45, quality as the issue and would_return 0.97 using 435 input tokens.

  • Check a listing before publication

    Send a listing title, description and required fields, then ask whether the title agrees with the description and whether a required detail appears. Use the resulting yes/no probabilities as publishing gates, with ambiguous listings held for a person.

  • Score a lead before escalation

    Pass an enquiry such as “We need a team rollout next month” with its supplied company and timing fields. Define ordered qualification levels and ask whether information is missing, then use scores and uncertainty to decide which leads need a generative follow-up.

Model reference

Jev 1.14 API reference

Jev 1.14 API specifications

Publisher and model
TypeSafe — Jev 1.14 (jev-1.14.0)
Release date
14 October 2026; previous build Jev 1.13
Public API name
typesafe/jev-1.14/decision
State input
String, JSON object or JSON array
Question types
noul, choice and score
Questions per call
Up to 64, independent and parallel
Context limits
64k tokens per request; 32k for state plus one question
Choice options
1–255 named options with descriptions
Score rubric
2–10 ordered levels, from low to high
Task output
output.decision contains answers and inputTokens
Observed latency
About 0.6 s in our calls; earlier probe 0.62 s
Billing unit
Measured input tokens; output tokens free

How to call the Jev 1.14 API

  1. Prepare the shared state

    Place the ticket, transcript or review in state as a string, JSON object or array. Include the evidence each question needs, since questions cannot read one another’s answers.

  2. Define typed questions

    Give each question a name, type and instructions; add criteria to describe choice options or ordered score levels. Choose noul for a yes/no probability, choice for a category or score for a rubric.

  3. Call the decision endpoint

    POST /api/v1/jobs/createTask?wait=30 with model set to typesafe/jev-1.14/decision and input containing state and questions. Read output.decision from the completed task, or create the task and poll recordInfo.

  4. Validate and route answers

    Compare probabilities and confidence with human labels on your own sample before choosing thresholds. Route uncertain cases to review and record inputTokens alongside the decisions.

The short version

Build your Jev 1.14 workflow around a judgment your code can use: a ticket category, a review score or the probability that an offer appears in a transcript. Start with the examples on this page, define criteria that match your own labels and compare uncertain answers with the original input. Keep the 64-question and context limits in view as you add checks. Use the reported inputTokens to track usage, consult the displayed price for the current rate and preserve a review path for decisions that need an explanation.

Jev 1.14 API questions