Does Jev 1.14 support zero data retention?

With abuse monitoring, yes. On TypeSafe AI through the Opper gateway, prompts and outputs are not used for training and are kept only for abuse monitoring.

Where is Jev 1.14 hosted?

See the per-route table for Jev 1.14 hosting locations and residency details.

Is Jev 1.14 trained on prompts and outputs?

No. Every hosting route for Jev 1.14 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Jev 1.14?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Jev 1.14. Contact hello@opper.ai to receive it.

Jev 1.14

by TypeSafe AI

Jev 1.14 returns typed judgments for software: true/false probabilities, choices from supplied options and scores against a rubric. TypeSafe describes this release as an incremental improvement over Jev 1.13, with its largest expected gain in multilingual support. It accepts text or structured text as a shared state. Default context limits are 64k tokens for the full request and 32k for the state plus any one question. Images and the new box question type are experimental, with a caller-supplied TypeSafe-Danger-Zone-Images header. Box returns normalized coordinates and confidence. Evaluate these opt-in features on your own inputs before production use.

Call Jev 1.14 on Opper through the System One evaluation API. Sign up without a credit card. Get started

Get your API key Evaluate via API Compare

Key info

Input

Output

Features

Context window

64K

Max output

—

Input price

$0.04 /1M

Output price

$0 /1M

Zero data retention with abuse monitoring
No training by default
GDPR DPA available

Available routes

Jev 1.14 runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
TypeSafe AI	Multi		No	$0.04	$0	Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=typesafe%2Fjev-1.14.0

Data handling per route

Each route hosting Jev 1.14 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

TypeSafe AI — United States🇺🇸

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention: With abuse monitoring, window not stated.
Training: No training on customer data.
Logging: Abuse monitoring
Subprocessor access: Subprocessors may read content
GDPR DPA: DPA available
Transfer mechanism: SCCs

Benchmarks

Jev 1.14 played 100 games of Pac-Man against the four arcade ghosts. It is level with Eevo-1.1 within the margin of error.

JevMan: the Pac-Man benchmark for AI decision models

Rank in our runs=1 of 11

Mean score3,597

Best game10,050

Games100

See the JevMan benchmark →Compare all decision modelsScores from Opper's own runs. Updated Oct 20, 2026.

Get started

Call Jev 1.14 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 and the TypeSafe API reference for question types and response formats. Compare every decision model, on one API.

Jev 1.14 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

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1curl https://api.opper.ai/v3/compat/v1/systemone \
2  -H "Authorization: Bearer $OPPER_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "typesafe/jev-1.14.0",
6    "state": "The customer cannot sign in and needs help immediately.",
7    "questions": {
8      "is_urgent": {
9        "type": "noul",
10        "instructions": "Does the customer need urgent help?"
11      }
12    }
13  }'