TypeSafe AI · Familia de modelos

Jev

TypeSafe AI decision model for typed choices, scores and probabilities. No generated prose; input-token billing applies. Evaluate accuracy on your own workload.

Solo API Texto Actual: Jev 1.13

Versión actual

Jev 1.13

Estable

Current documented version checked September 24, 2026. Outputs typed decisions, not prose. Official announcement dates the Jev family launch, not a separately verified release date for this version.

Fecha de publicaciónFecha no proporcionada
Ventana de contexto64K tokens
LicenciaProprietary hosted API
PesosNo publicado

Especificaciones verificadas

Input price USD 0.042 per million input tokens Fuente →
Output billing Output tokens are free; input is billed Fuente →
State plus longest question 32k tokens; total request budget 64k Fuente →
Output types Choice, Score, Noul; typed decisions, not generated text Fuente →
Language support English is primary; test non-English workloads independently Fuente →
Parameter count Not disclosed in reviewed documentation Fuente →

Cronología de lanzamientos

Jev 1.13
Estable · Fecha no proporcionada

Current documented version checked September 24, 2026. Outputs typed decisions, not prose. Official announcement dates the Jev family launch, not a separately verified release date for this version.

64K de contexto Solo API

Anuncio oficial →

Proyectos

Official agent skills for designing applications around TypeSafe typed decisions. Development guidance complements the runtime SDKs and API.

★ 2K · ⑂ 109

Integrate TypeSafe decisions into JavaScript and TypeScript services. Answer types are inferred from questions; the package supports ESM and CommonJS.

★ 231 · ⑂ 25

Connect Python services to the TypeSafe API using typed questions and results. The repository provides the client library rather than model weights.

★ 218 · ⑂ 30

Artículos relacionados

Jev是什么:Almeida团队推出只做结构化判断的AI模型 sept. 24, 2026 把Jev接入应用:官方Python、JavaScript SDK与Agent工具链 sept. 24, 2026 Jev适合什么、不适合什么:中文、长上下文与判断阈值 sept. 24, 2026