TypeSafe AI Launches Jev 1.14 with Image Support, Box Type, and 262k Context
October 14, 2026 — TypeSafe AI has released Jev 1.14, the latest version of its System One decision model. Now live under the jev-preview alias, this update introduces three experimental 'danger zone' features: image input, a new box type, and extended context. For developers, Jev 1.14 pushes a typed decision model toward vision tasks such as inspection and localization.
⚠️ Important: None of the three features are production-ready yet, as TypeSafe notes in its release.
TL;DR: Jev 1.14
- Size: Parameters not disclosed. Context defaults to 64k tokens per request and 32k per question, but can be extended to 262k with an opt-in header.
- Availability: Hosted API only (
POST /v1/systemone). No open weights; hardware and quantized variants are not disclosed. - Performance: Small improvements across the board, with the largest gains in multilingual support (TypeSafe's claim, no public scores provided).
- Best result: In TypeSafe's Box test, four edge-check questions caught 30 of 36 cut-off crops.
- Worst caveat: Images and Box are not production-ready, and Box lacks a 'not found' answer option.
What is Jev 1.14?
Jev is a System One model from TypeSafe AI that returns typed decisions instead of generated text. You send a state along with typed questions: Choice, Score, or Noul. Jev answers each with a typed value, probabilities, and a confidence score.
TypeSa...
via MarkTechPost