LuckyBricks
285 posts

LuckyBricks
@Lucky_Brick
Programming, Photography, Anime | ex-full stack developer, reseaching on devtools and produtivity booster | Linux enthusiast
2026 Yıllık Özeti
@Lucky_Brick hesabının Twitter yılını gör

Most LLM cost savings come from prompt caching, not automatic model routing. Cache is per-model KV state,switch models and it's a full cache miss on your system prompt, even if the text is identical. The real win is cache-aware routing that never routes away from your warm cache






Kimi K3 is now available on Token Factory. We’re excited to announce that Nebius Token Factory is an official Day 0 partner for @Kimi_Moonshot's Kimi K3. Kimi K3 is the first open-weight model to reach frontier-level performance, a major step forward for open models. It is built for long-horizon coding, knowledge work and reasoning, with native vision and up to 1M tokens of context. Artificial Analysis scores it at 57 on its Intelligence Index, just two points behind GPT-5.6 Sol (max). That puts Kimi K3 at the top of the open-weight field and firmly among today’s frontier models. Developers can access K3 through Token Factory’s OpenAI-compatible API and console today. Give K3 the hard problem. Build with Kimi K3: tokenfactory.nebius.com/?modals=endpoi…



k3马上就开源了,花两三百买kimi白号,脑袋被驴踢了么
















