Clade Cost Tuning

Anthropic Cost Tuning

Overview

Anthropic charges per token. Input tokens, output tokens, and cached tokens each have different prices. Here's how to minimize cost without losing quality.

Pricing (per million tokens)

Cost Reduction Strategies

Instructions

Step 1: Right-Size Your Model

// DON'T use Opus for everything
// DO match model to task complexity:

// Simple classification/extraction → Haiku (cheapest)
const category = await classify(text, 'claude-haiku-4-5-20251001');

// General coding/writing → Sonnet (balanced)
const code = await generate(spec, 'claude-sonnet-4-20250514');

// Complex multi-step reasoning → Opus (best quality)
const analysis = await analyze(data, 'claude-opus-4-20250514');

Step 2: Prompt Caching (90% off input tokens)

// Cache your system prompt — pays for itself after 2 calls
const message = await client.messages.create({
  model: 'claude-sonnet-4-20250514',
  max_tokens: 1024,
  system: [{
    type: 'text',
    text: longSystemPrompt, // Must be 1024+ tokens
    cache_control: { type: 'ephemeral' }, // Cache for 5 minutes
  }],
  messages,
}, {
  headers: { 'claude-beta': 'prompt-caching-2024-07-31' },
});

// First call: cache_creation_input_tokens charged at 1.25x
// Subsequent calls: cache_read_input_tokens charged at 0.1x (90% savings!)

Step 3: Message Batches (50% off everything)

// For non-urgent work — 50% cheaper, 24h processing SLA
const batch = await client.messages.batches.create({
  requests: prompts.map((p, i) => ({
    custom_id: `job-${i}`,
    params: {
      model: 'claude-sonnet-4-20250514',
      max_tokens: 1024,
      messages: [{ role: 'user', content: p }],
    },
  })),
});
// Sonnet: $1.50/$7.50 per MTok instead of $3/$15

Step 4: Reduce Token Count

// Trim conversation history — keep system + last N turns
function trimMessages(messages: MessageParam[], maxTurns = 10) {
  if (messages.length <= maxTurns * 2) return messages;
  return messages.slice(-(maxTurns * 2));
}

// Set tight max_tokens — don't pay for output you won't use
const message = await client.messages.create({
  model: 'claude-sonnet-4-20250514',
  max_tokens: 256, // Not 4096 if you only need a short answer
  messages,
});

// Use concise system prompts
system: 'Reply in 1-2 sentences.' // Not a 500-word personality description

Step 5: Monitor Usage

// Log every call's cost
function logUsage(message: Anthropic.Message) {
  const { input_tokens, output_tokens } = message.usage;
  const cost = (input_tokens * 3 + output_tokens * 15) / 1_000_000; // Sonnet pricing
  console.log(`Tokens: ${input_tokens}in/${output_tokens}out | Cost: $${cost.toFixed(4)}`);
}

Cost Comparison Example

Processing 10,000 documents (avg 500 tokens each, 200 token response):

Output

• Model selection optimized per task complexity (Haiku for simple, Sonnet for balanced, Opus for complex)
• Prompt caching enabled for repeated system prompts
• Batch processing configured for non-urgent workloads
• Token usage logged with cost estimates per request
• Spending alerts configured in Anthropic console

Error Handling

Examples

See Pricing table, five numbered strategy sections with code, and the Cost Comparison Example table showing savings from $225 to $5 for 10K documents.

Resources

• Pricing
• Prompt Caching
• Message Batches
• Token Counting

Next Steps

See clade-performance-tuning for latency optimization.

Prerequisites

• Completed clade-install-auth
• Active API usage to optimize
• Access to Anthropic console for usage monitoring

Source: jeremylongshore/claude-code-plugins-plus-skills → skills/.curated/clade-cost-tuning/SKILL.md

Also appears in: jeremylongshore/claude-code-plugins-plus-skills/plugins/saas-packs/claude-pack/skills/clade-cost-tuning/SKILL.md