Solar Pro 3 is Upstage's efficient large language model, building on Solar Pro 2 with Upstage's SnapPO reinforcement learning framework to sharpen step-by-step reasoning in math, code, and agentic tasks. It roughly doubles agentic benchmark performance over its predecessor while keeping the same API and serving footprint, with strong multilingual (notably Korean) support.
费用比率
0.1x
上下文
131K
发布日期
2026年1月27日
输入
Text
输出
Text
支持
推理工具调用结构化输出
性能
根据近期请求测得的中位延迟和吞吐量。
吞吐量142 tok/s
延迟1.27s
关于 Solar Pro 3 的最新资讯
近期文章和社区帖子,均链接至原始来源。
작은 AI, 기억을 묶었더니 학습이 빨라졌다? | Solar Mini 4.5 PreviewSung Kim1,201