How it works
Every message is classified into one of five task types:| Task Type | Examples | Default Model |
|---|---|---|
| Code | Debugging, PR review, refactoring, scripts | Claude Sonnet 4.6 |
| Research | Web search, competitor analysis, summarizing articles | Claude Sonnet 4.6 |
| Summary | TL;DR, key points, digest | Claude Haiku 4.5 |
| Creative | Blog posts, emails, newsletters, copy | Claude Opus 4.6 |
| Chat | General Q&A, quick questions | Claude Haiku 4.5 |
- Per-task override — if you’ve pinned a specific model to a task type, it always wins
- Self-learning — if enough samples have been collected, the router uses the model with the highest success rate
- Budget fallback — if your monthly budget is above the threshold, non-critical tasks switch to the fallback model
- Ollama routing — background tasks can be sent to a local Ollama model at zero API cost
- Task-type defaults — the table above
Configure the router
Go to Settings → Model Router.Primary and fallback models
Primary Model is used for most tasks. Sonnet 4.6 is a good default — capable enough for most work, cheaper than Opus. Budget Fallback Model kicks in when your monthly budget exceeds the threshold. Haiku is the recommended fallback — fast and very cheap.Budget threshold
The slider controls what percentage of your monthly budget triggers the fallback. Default is 80% — meaning the last 20% of your budget is protected for critical tasks.Self-learning
When enabled, the router tracks which models succeed or fail on each task type. After collecting enough samples (default: 20), it automatically adjusts routing to prefer higher-performing models. To prevent self-learning from changing routing for a task type, click the lock icon next to that task in the per-task overrides table.Ollama (local models)
If you run Ollama locally, the router can send background tasks (summaries, chat) to a local model instead of the API — reducing cost to zero for those task types. Enable it in Settings → Model Router → Local Ollama Routing and set your Ollama base URL (default:http://localhost:11434).
Recommended local model: llama3.2 for general use, codellama for code tasks.
Disable the router
Toggle Model Router off in Settings. All agents will use the primary model for every task.Per-agent overrides
Agents can also have a model set directly in Team → [Agent] → Settings → Model. An explicit agent-level model always takes priority over the router.Environment variables
| Variable | Default | Description |
|---|---|---|
MODEL_ROUTER_ENABLED | true | Master switch |
MODEL_ROUTER_PRIMARY | anthropic/claude-sonnet-4-6 | Primary model |
MODEL_ROUTER_FALLBACK | anthropic/claude-haiku-4-5 | Budget fallback |
MODEL_ROUTER_BUDGET_THRESHOLD | 80 | Fallback trigger % |
OLLAMA_BASE_URL | http://localhost:11434 | Ollama endpoint |