Model Routing

Not every task needs your strongest model. This is the single biggest cost lever.

Route by Task, Not by Default

Task Type	Model Tier	Examples
Heartbeats, monitoring, routine checks	Cheap (Haiku, Gemini Flash)	Health pings, calendar scans, email checks
Standard work, conversations, tool use	Mid-tier (Sonnet, GPT-5.4)	Chat, research, file operations
Complex reasoning, architecture, planning	Premium (Opus)	Design docs, multi-step analysis, code review

Set your default model to the cheapest one that reliably follows instructions. Override to stronger models per-agent or per-cron where reasoning quality actually matters. Operators have seen prompt costs drop from 20-40k tokens to ~1.5k per request by routing smarter.

Configuration

{
  "agents": {
    "defaults": {
      "model": {
        "primary": "openai-codex/gpt-5.4",
        "fallbacks": ["anthropic/claude-sonnet-4-6"]
      }
    },
    "list": [
      {
        "id": "main",
        "model": { "primary": "anthropic/claude-opus-4-6" }
      }
    ]
  }
}

The main (interactive) agent gets the premium model. Everything else starts cheap and gets upgraded only where quality suffers.

For model behavioral differences (tool compliance, writing quality, failure modes), see Model Behavioral Differences.

For advanced routing patterns (scout/dispatch, thinking parameters, fallback chains), see Model Optimization.