Show HN: YPerf – Monitor LLM Inference API Performance
Our team operates several real-time AI applications, where both latency(TTFT) and throughput(TPS) are critical to most of our users. Unfortunately, nearly all of the major LLM APIs lack consistent stability.
To address this, I developed YPerf—a simple webpage designed to monitor the performance of inference APIs. I hope it helps you select better models and discover new trending ones as well.
The data is sourced from OpenRouter, an excellent provider that aggregates LLM API services.
(
2 comments
| on HN
)
---
Great suggestion!
I currently pick the fastest TPS among providers, and you can see a detail performance list by clicking the <Learn More> icon at the last column. For example, here's the detailed OR page of Llama 3.3: https://openrouter.ai/meta-llama/llama-3.3-70b-instruct
I'll add the filtering soon.