clade-performance-tuning
Installation
SKILL.md
Anthropic Performance Tuning
Overview
Claude latency has two components: time to first token (TTFT) and tokens per second (TPS). Different strategies target each.
Latency Benchmarks (approximate)
| Model | TTFT (p50) | TTFT (p95) | Output TPS |
|---|---|---|---|
| Claude Haiku 4.5 | 200ms | 600ms | ~150 |
| Claude Sonnet 4 | 400ms | 1.2s | ~90 |
| Claude Opus 4 | 800ms | 2.5s | ~40 |