Typesafe · Decision
Jev 1.14.0
Jev is a System One decision model from TypeSafe: instead of generating text it returns typed answers (yes/no, choice, score) with calibrated probabilities for routing, classification and other in-app decision points. Version 1.14 improves across the board, most in languages other than English, and adds experimental images and Box questions (where something is in an image).
Evidence and sources
Released 14 Oct 2026
All rankings:
#17 on OpenRouter today
#18 on OpenRouter this month
#21 on OpenRouter this weekSources: TypeSafe Models Docs data docs, Vercel AI Gateway data, AI/ML API data, llminfo researchPrimary data from TypeSafe Models Docs
from Vercel AI Gateway: name
from AI/ML API: description
from llminfo research: release date
Advantages and trade-offs
Compared with 10 representative decision models
Advantages
Advertised function calling support
Function calling advertised by 3 of the 6 peers that list their features.
Input & output
Inputs as stated by providers; output from the model’s typeText
Images
Choices and scores
Also known as: databricks-typesafeai-jev-1-14-0, databricks/databricks-typesafeai-jev-1-14-0, jev-1.14, typesafe-ai/jev-1.14.0, typesafe/jev-1.14, typesafe/jev-1.14.0, vercel_ai_gateway/typesafe-ai/jev-1.14.0
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works