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.
Cost rate
0.1x
Context
131K
Released
Jan 27, 2026
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Performance
Median latency and throughput measured across recent requests.
Throughput142 tok/s
Latency1.27s
Latest news about Solar Pro 3
Recent articles and community posts, linked to their original sources.
