Định tuyến thông minh

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Summarize this article...' }],
  routing: {
    strategy: 'cost_optimized',
  },
});

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Quick answer needed...' }],
  routing: {
    strategy: 'latency_optimized',
  },
});

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Write a detailed analysis...' }],
  routing: {
    strategy: 'quality_optimized',
  },
});

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }],
  routing: {
    fallback: ['claude-3.5-sonnet', 'gemini-2.0-flash'],
  },
});

const response = await client.chat.completions.create({
  model: 'gpt-4o-mini',
  messages: [{ role: 'user', content: 'Hello!' }],
  routing: {
    allow_upgrade: true,
  },
});

const response = await client.chat.completions.create({...});

console.log(response.openmodex?.provider);          // "openai"
console.log(response.openmodex?.routing_strategy);   // "cost_optimized"
console.log(response.openmodex?.fallback_used);      // false
console.log(response.openmodex?.latency_ms);         // 850