Routing

Routing rules determine how jobs are matched to workers. You can route by provider, model, priority, tags, cost tier, or custom logic.

Default behavior

Without routing rules, jobs go to the first available worker that supports the requested provider.

Tiered routing

Route by job complexity:

{
  "routing": {
    "tiers": {
      "low": { "provider": "ollama", "model": "llama3.2" },
      "medium": { "provider": "claude", "model": "haiku" },
      "high": { "provider": "claude", "model": "sonnet" }
    }
  }
}

Dispatch with a tier:

modelreins job dispatch --tier low --prompt "Classify this text"

Tag-based routing

Match jobs to workers by tags:

{
  "routing": {
    "rules": [
      { "match": { "tag": "code-review" }, "workers": { "tag": "gpu-server" } },
      { "match": { "tag": "summarize" }, "workers": { "tag": "local" } }
    ]
  }
}

Fallback chains

Try providers in order:

{
  "routing": {
    "strategy": "fallback",
    "chain": ["ollama", "claude", "openrouter"]
  }
}

Budget routing

Enforce spend limits with automatic downgrade to local:

{
  "routing": {
    "budget": {
      "weekly_limit_usd": 5.00,
      "over_budget_provider": "ollama"
    }
  }
}

See Cost Optimization for strategies built on routing.