// 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');

// 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!)

// 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

// 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

// 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)}`);
}