Nexith Core가 자체 주권 GPU 클러스터에서 서비스 시작 —— 캐시 히트 최대 90% 할인, OpenAI 호환.자세히 보기
Nexith
시작하기
Changelog

What’s new.

The things we’ve shipped, most recent first. We list what’s actually live — nothing more.

August 2026
New

Nexith Chat

Chat with Nexith Core in the browser — long context, streaming responses, and memory that carries across sessions.

Improved

Privacy egress gate

Every response — streaming, non-streaming, or served from cache — now passes a single allowlist gate on the way out.

July 2026
New

Session memory

Pinned facts and auto-captured context, scoped per user and per app, retrieved at request time.

New

Semantic cache

Requests close to one already answered are replayed from cache in milliseconds — cached input billed at up to 90% off on a hit.

June 2026
New

OpenAI-compatible API

Point your existing SDK at our endpoint. Chat completions and embeddings, with SSE streaming on every endpoint.

New

Usage analytics & API keys

Dashboards for token usage and cost, plus fine-grained keys with scoped permissions and per-key rate limits.

Nexith — 프론티어 AI 모델 | Nexith