Upstage Status

loading…
ComponentsUptime over the past 90 days

LLM Performance

loading…

Time to First Token (TTFT)

lower is better · ms · p50

Throughput (TPS)

higher is better · tok/s · p50

The performance figures above are collected by periodically probing each model with a prompt of roughly 1,000 tokens and measuring the response. Actual latency and throughput may differ from your real-world experience depending on prompt size, concurrency, and workload.