OpenRouter Performance Tuning Overview OpenRouter adds minimal overhead ( 50-100ms) to direct provider calls. Most latency comes from the upstream model. Key levers: model selection (smaller = faster), streaming (lower TTFT), parallel requests, prompt size reduction, and provider routing to faster infrastructure. This skill covers benchmarking, streaming optimization, concurrent processing, and connection tuning. Benchmark Latency Streaming for Lower TTFT Parallel Request Processing Performance Optimization Checklist | Optimization | Impact | Effort | |-------------|--------|--------| | Use s…