# TypeSafe AI puts Jev's first bounding-box output behind an API flag

> Source: <https://runtimewire.com/article/typesafe-jev-1-14-danger-zone-experiments>
> Published: 2026-10-16 10:03:35+00:00

# TypeSafe AI puts Jev's first bounding-box output behind an API flag

**Jev 1.14.0 enters preview with longer-context access, while CEO Diogo Almeida keeps image and bounding-box features behind experimental API flags.**

        By [RuntimeWire Staff](https://runtimewire.com/author/runtimewire-staff)
        · Published 

Primary source: [TypeSafe AI](https://typesafe.ai/blog/jev-1-14)

## Why it matters

TypeSafe is opening Jev to image and spatial tasks while withholding a production reliability guarantee. The release tests whether developers can use typed AI decisions beyond simple classification while maintaining the reliability the company promises.

[TypeSafe AI](https://typesafe.ai/?ref=runtimewire), the company co-founded by Diogo Almeida, released Jev 1.14.0 on October 14th with a bounding-box output and opt-in access to longer context, according to its [release post](https://typesafe.ai/blog/jev-1-14?ref=runtimewire). TypeSafe's [model documentation](https://docs.typesafe.ai/models?ref=runtimewire) also lists Jev 1.14 as available from October 14th. Jev 1.13.0 already supported image inputs.…