> ## Documentation Index
> Fetch the complete documentation index at: https://docs.51ultron.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Model Routing

> How Ultron routes tasks between Kimi K2 and fast models based on complexity and cost.

Not every task needs the same model. Ultron routes requests to the right model based on what the task actually requires — keeping complex reasoning powerful and simple lookups fast.

## Routing logic

| Task type                      | Model      | Rationale                               |
| ------------------------------ | ---------- | --------------------------------------- |
| Research, competitive analysis | Kimi K2    | Deep reasoning, multi-source synthesis  |
| Cold email, content creation   | Kimi K2    | Voice matching, quality gate compliance |
| Objection handling, strategy   | Kimi K2    | Nuanced reasoning, context awareness    |
| Lead scoring                   | Fast model | Pattern matching, high throughput       |
| Quick lookups, summaries       | Fast model | Speed matters, complexity doesn't       |
| Routing decisions              | Fast model | Lightweight classification              |
| Memory compression             | Fast model | Summarization at scale                  |

## How routing is decided

The decision happens before the API call based on:

1. **Message complexity** — length, number of entities, implied reasoning depth
2. **Task type** — skill runs always use the model specified in their `SKILL.md` config
3. **User plan** — free plan routes more aggressively to fast models
4. **Token estimate** — very short tasks default to fast even if complex-looking

## Credit impact

Kimi K2 costs more per token than the fast model. The routing system keeps your credits efficient by:

* Routing memory compression, scoring, and routing decisions to the fast model
* Reserving Kimi K2 for tasks where output quality directly affects business outcomes
* Giving you visibility into model usage per session in **Settings → Usage**

<Info>
  Each skill's `SKILL.md` file specifies which model it uses. Research and sales skills use Kimi K2. Ops skills like morning briefing and pipeline review use the fast model.
</Info>