TypeSafe AI · Model family

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 only Text Current: Jev 1.13

Current release

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.

Release dateDate not provided
Context window64K tokens
LicenseProprietary hosted API
WeightsNot published

Verified specifications

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 →

Release timeline

Jev 1.13
Stable · Date not provided

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 API only

Official announcement →

Projects

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

Related articles

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