Skip to main content
The Model Router automatically selects the right model for each task — routing cheap tasks to cheaper models and complex tasks to more capable ones. It learns from outcomes over time.

How it works

Five-tier priority system, evaluated in order:
  1. Task-type override — if you’ve pinned a specific model to a task type, that wins
  2. Self-learning — if a model has a strong success record for this task type (min 20 samples), use it
  3. Budget fallback — if monthly spend exceeds your threshold, downgrade non-critical tasks to Haiku
  4. Ollama — if Ollama is running locally and the task is eligible (summary, chat), route there
  5. Task-type defaults — built-in sensible defaults per task type

Default routing

Configuration

Configure in Settings → Model Router in the dashboard, or directly in ~/.openclaw/openclaw.json:

Options