TypeSafe AI · Famille de modèles

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 uniquement Texte Actuelle : Jev 1.13

Version actuelle

Jev 1.13

Stable

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.

Date de sortieDate non fournie
Fenêtre de contexte64K jetons
LicenceProprietary hosted API
PoidsNon publiés

Spécifications vérifiées

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

Chronologie des versions

Jev 1.13
Stable · Date non fournie

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.

contexte 64K API uniquement

Annonce officielle →

Projets

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

Articles associés

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