clade-performance-tuning

name	clade-performance-tuning
description	Optimize Anthropic API latency — streaming, prompt caching, model selection, Use when working with performance-tuning patterns. connection reuse, and parallel requests. Trigger with "anthropic slow", "claude latency", "speed up anthropic", "anthropic performance", "claude response time".
allowed-tools	Read, Write, Edit
version	1.0.0
license	MIT
author	Jeremy Longshore <[e-mail]>
compatible-with	claude-code
tags	["saas","anthropic","claude","performance","latency"]

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

Optimization Strategies

Instructions

Step 1: Always Stream

// Streaming delivers the first token ASAP — user sees response instantly
// instead of waiting for the full response to generate

const stream = client.messages.stream({
  model: 'claude-sonnet-4-20250514',
  max_tokens: 1024,
  messages,
});

// First token arrives in ~400ms (Sonnet)
// Full response may take 5-10s, but user sees progress immediately
for await (const event of stream) {
  if (event.type === 'content_block_delta') {
    yield event.delta.text;
  }
}

Step 2: Prompt Caching — Faster TTFT

// Cached prompts skip re-processing — dramatically lower TTFT for large system prompts
const message = await client.messages.create({
  model: 'claude-sonnet-4-20250514',
  : ,
  : [{
    : ,
    : largeSystemPrompt, 
    : { :  },
  }],
  messages,
}, {
  : { :  },
});