AI KNOWLEDGE DESK

Models · entities · concepts · comparisons · practical tools

GETLLMS.ORG

Jev 1.13

Jev 1.13 is TypeSafe's text-only System One Model for fast typed probabilities and decisions, not generated prose, code or explanations.

Decision ModelText ClassificationStructured OutputAgent RoutingLow Latency
TypeSafe hosted API
$0.042 per 1M input tokens; output tokens free
Commercial

🚀Function Overview

A text-only decision model for ranking, routing, filtering, scoring and other bounded choices where compact calibrated probabilities are more useful than generated prose.

Key Features

  • Current dated model ID jev-1.13.0
  • Moving alias jev-latest currently points to Jev 1.13
  • POST /v1/systemone request surface
  • Typed Choice, Score and Noul decision primitives
  • Text, strings, JSON-like state and arrays as input; no image, audio or video input
  • Probability and typed decision output; no prose, code or reasoning explanation generation
  • 64,000-token overall request limit documented by TypeSafe
  • 32,000-token state budget plus the longest question
  • $0.042 per million input tokens with no output-token charge
  • English is the primary language; CJK support is documented as uneven
  • Customer requests and responses are not used for training; zero-data-retention is an enterprise option
  • Group-level calibration requires task-specific thresholds and fallbacks

Use Cases

  • Rank candidate actions, documents, code paths or search results
  • Route a request to a model, tool, workflow or human reviewer
  • Filter browser content and agent tool output
  • Score policy, relevance, quality or safety criteria
  • Choose navigation edges in browser, desktop and graph agents
  • Triage cases before a slower reasoning or generative model

⚙️Input Parameters

model

string

Use jev-1.13.0 to pin the dated model or jev-latest for TypeSafe's moving alias.

state

string | object | array

Textual context, strings, JSON-like objects or arrays that describe the item or environment being judged.

questions

array

Typed Choice, Score or Noul questions and their allowed labels, options or scale.

💡Usage Examples

Example 1

Input Parameters

{
  "model": "jev-1.13.0",
  "state": "The user asks the agent to summarize a public document and provides a valid URL.",
  "questions": [
    {
      "type": "choice",
      "prompt": "Which route should handle this request?",
      "options": [
        "read-only fetch",
        "write-enabled browser",
        "human review"
      ]
    }
  ]
}

Output Results

A typed probability distribution over the allowed routes. Application code must choose and validate the threshold; Jev does not execute the route or explain the decision.