TypeSafe AI · Семейство моделей

Jev

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

Только API Текст Текущая: Jev 1.13
Официальный сайт →
Сравнить Документация для разработчиков Документация для разработчиков

Текущий релиз

Jev 1.13

Стабильный

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.

Дата выпускаДата не указана
Контекстное окно64K токенов
ЛицензияProprietary hosted API
ВесаНе опубликовано

Проверенные характеристики

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

Хронология релизов

Jev 1.13
Стабильный · Дата не указана

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 контекста Только API

Официальное объявление →

Проекты

typesafe-ai/skills Официальные

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

★ 2K · ⑂ 109
typesafe-ai/typesafe-sdk-js Официальные

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

★ 231 · ⑂ 25
typesafe-ai/typesafe-sdk-python Официальные

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

★ 218 · ⑂ 30

Связанные статьи

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