TypeSafe AI · 모델 제품군

Jev

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

API 전용 텍스트 현재: Jev 1.13

현재 릴리스

Jev 1.13

안정

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.

릴리스 날짜날짜 미제공
컨텍스트 창64K 토큰
라이선스Proprietary hosted API
웨이트미공개

검증된 사양

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

릴리스 타임라인

Jev 1.13
안정 · 날짜 미제공

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.

컨텍스트 64K API 전용

공식 발표 →

프로젝트

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

관련 기사

Jev是什么:Almeida团队推出只做结构化判断的AI模型 9월 24, 2026 把Jev接入应用:官方Python、JavaScript SDK与Agent工具链 9월 24, 2026 Jev适合什么、不适合什么:中文、长上下文与判断阈值 9월 24, 2026