perplexity-load-scale
Installation
SKILL.md
Perplexity Load & Scale
Overview
Load testing and capacity planning for Perplexity Sonar API. Key constraint: Perplexity rate limits at 50 RPM (default tier), and every request performs a live web search with variable latency. Load testing must respect these limits to avoid burning through credits.
Capacity Constraints
| Constraint | Default Limit | Impact |
|---|---|---|
| RPM (requests per minute) | 50 | Hard ceiling on throughput |
| Context window | 127K tokens | Limits conversation history |
sonar latency |
1-3s | Throughput: ~20-50 concurrent |
sonar-pro latency |
3-8s | Throughput: ~6-16 concurrent |
search_domain_filter |
20 domains max | Per-request limit |