Models / Jev

Jev

edge
TypeSafe → Find for my hardware

Decision model. Reads typed options from the logits, returns typed answers with probabilities in one pass. Three shapes: yes/no probability, choice from a set, score on a scale. No text generation, nothing to parse. RLCD training against proper scoring rules.

AI-generated content marks

The provider reports that this model does not add embedded watermarks or provenance metadata to generated output.

general chat
Context
60k
License
proprietary
Developer
TypeSafe
Released
Sep 2026

Related models

JEV-35B
35.0B 3.0B active consumer 20GB min RAM Oct 11, 2026
JEV-27B-VL
27.8B enthusiast 16GB min RAM Sep 30, 2026

Guides covering Jev

Microsoft built its decision model on Alibaba's weights Oct 11, 2026 Ollama 0.35 ships the Jev API locally: pull Nimble or Tev1 Sep 30, 2026 What is Jev? The plain-English guide Sep 20, 2026

Save your hardware and every model page answers the real question: will it run on your machine, and how fast?

Join free - save your rig →

Or run it in the cloud

Live per-provider pricing, throughput and uptime. Click a column to sort.

Provider Type Input $/M Output $/M Cache $/M Tok/s Latency Uptime Value
OpenRouter
API 0.04 0.00 - - - - cheapest

Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.

Detailed API pricing page + JSON endpoint →

PRICE HISTORY

Inference cost over time

Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.

Loading price history...