---
last_updated: 2026-11-22
source_url: https://opper.ai/typesafe/jev-1-13-0
title: "Jev 1.13 by TypeSafe AI"
description: "Jev 1.13 is TypeSafe AI's System One model: it answers true/false, choice and rubric-score questions with calibrated probabilities instead of writing text."
---

# Jev 1.13

By [TypeSafe AI](https://opper.ai/typesafe).

Released 15 Sep 2026 · [Announcement](https://typesafe.ai/blog/introducing-system-one-models-and-jev) · [All TypeSafe AI releases](https://opper.ai/model-releases/typesafe)

Jev 1.13 is the current release of Jev, TypeSafe AI's flagship and the first of its System One models, named after the fast, intuitive thinking Daniel Kahneman described in Thinking, Fast and Slow. Instead of generating text for a person to read, it makes judgments for software to act on: you send a state (a string, a JSON object or an array of text) with a set of questions, and it returns typed answers with probabilities, not prose.

Noul questions return the probability that a statement is true, Choice picks from options you define, and Score places the state on your own rubric, the last two with a full probability distribution and a confidence value. TypeSafe trains Jev with its own method, Reinforcement Learning for Calibrated Decisions (RLCD), so its probabilities are tuned against real outcomes. Every question is evaluated in parallel and in isolation against the same state, so adding questions barely changes latency.

Jev is built for atomic questions composed in code: ticket classification and routing, intent detection, guardrail checks and rubric scoring in place of an LLM judge, with confidence deciding what runs automatically and what escalates to a person or a reasoning model. Input is text only and accuracy is strongest in English. A request holds 64K tokens in total, with at most 32K for the state plus the longest question.

## Available routes

Jev 1.13 runs on 1 route through the Opper gateway. Prices are per 1M tokens. Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=typesafe%2Fjev-1.13.0.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [TypeSafe AI](https://opper.ai/provider/typesafe) | `typesafe/jev-1.13.0` | Multi (United States) | Retained | No | $0.04 | n/a | Input price |

## Key info

- Model id: `typesafe/jev-1.13.0`
- Input: Text
- Output: Text
- Features: none listed
- Context window: 64K
- Input price: $0.04 per 1M tokens
- Released: 15 Sep 2026
- No training by default

## Data handling per route

Each route hosting Jev 1.13 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### TypeSafe AI — United States

Content is retained: provider logging. No training on customer data. GLOBAL; SCCs.

- Zero data retention: Retained: provider logging.
- Training: No training on customer data.
- Logging: Other
- Subprocessor access: Subprocessors may read content
- Transfer mechanism: SCCs

Verified by Opper on 2026-11-02.

## Best for

Listed in [Decision models](https://opper.ai/models/decision-models).

## Benchmarks

Jev 1.13 played 100 games of Pac-Man against the four arcade ghosts.

### JevMan: the Pac-Man benchmark for AI decision models

- Rank in our runs: 10 of 19
- Mean score: 2,750
- Best game: 6,380
- Games: 100

Scores from Opper's own runs. Updated Nov 12, 2026. [See the JevMan benchmark](https://opper.ai/jevman-benchmark/) · [Watch Jev 1.13's game](https://opper.ai/jevman-benchmark/?pacman=typesafe%2Fjev-1.13.0) · [Compare all decision models](https://opper.ai/models/decision-models#benchmarks)

## Get started

Call Jev 1.13 through the Opper gateway with one API key. Evaluate state against typed questions using TypeSafe’s System One API for yes/no decisions, classification, and rubric scoring.

See the [Opper evaluation guide](https://docs.opper.ai/build/gateway/evaluations) and the [TypeSafe API reference](https://docs.typesafe.ai/api) for question types and response formats. [Compare every decision model](https://opper.ai/models/decision-models), on one API.

Jev 1.13 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Read https://docs.opper.ai/build/gateway/evaluations and call Jev 1.13 through Opper's System One evaluation endpoint using state and typed questions.
```

### Or call it directly

cURL:

```bash
curl https://api.opper.ai/v3/compat/v1/systemone \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "typesafe/jev-1.13.0",
    "state": "The customer cannot sign in and needs help immediately.",
    "questions": {
      "is_urgent": {
        "type": "noul",
        "instructions": "Does the customer need urgent help?"
      }
    }
  }'
```

## Use Jev 1.13 in your apps

Pick your tool to see how to run it on Jev 1.13 through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/jev-1-13-0)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/jev-1-13-0)
- [Codex](https://opper.ai/apps/codex/jev-1-13-0)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/jev-1-13-0)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/jev-1-13-0)
- [Aider](https://opper.ai/apps/aider/jev-1-13-0)
- [Goose](https://opper.ai/apps/goose/jev-1-13-0)
- [Droid](https://opper.ai/apps/droid/jev-1-13-0)
- [OpenCode](https://opper.ai/apps/opencode/jev-1-13-0)
- [Pi](https://opper.ai/apps/pi/jev-1-13-0)
- [OpenClaw](https://opper.ai/apps/openclaw/jev-1-13-0)
- [Hermes](https://opper.ai/apps/hermes/jev-1-13-0)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/jev-1-13-0)
- [OmniRoute](https://opper.ai/apps/omniroute/jev-1-13-0)
- [Cursor](https://opper.ai/apps/cursor/jev-1-13-0)
- [Cline](https://opper.ai/apps/cline/jev-1-13-0)
- [Continue](https://opper.ai/apps/continue/jev-1-13-0)
- [Kilo Code](https://opper.ai/apps/kilo-code/jev-1-13-0)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/jev-1-13-0)
- [Zed](https://opper.ai/apps/zed/jev-1-13-0)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/jev-1-13-0)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/jev-1-13-0)
- [n8n](https://opper.ai/apps/n8n/jev-1-13-0)
- [LibreChat](https://opper.ai/apps/librechat/jev-1-13-0)
- [Open WebUI](https://opper.ai/apps/open-webui/jev-1-13-0)
- [See all apps](https://opper.ai/apps)

## Other models from TypeSafe AI

- [Jev 1.14](https://opper.ai/typesafe/jev-1-14-0)
