TypeSafe AI · Modelfamilie

Jev

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

Alleen API Tekst Huidig: Jev 1.13

Huidige release

Jev 1.13

Stabiel

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.

ReleasedatumDatum niet opgegeven
Contextvenster64K tokens
LicentieProprietary hosted API
GewichtenNiet gepubliceerd

Geverifieerde specificaties

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

Release-tijdlijn

Jev 1.13
Stabiel · Datum niet opgegeven

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 context Alleen API

Officiële aankondiging →

Projecten

typesafe-ai/skills Officieel

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

Gerelateerde artikelen

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