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

# Routing modes

> Select the quality, latency, and cost posture for each request.

Tokenless offers three routing modes. Set one in the `model` field for each
request:

| Model                   | Best for                         | Behavior                                        |
| ----------------------- | -------------------------------- | ----------------------------------------------- |
| `tokenless-pro`         | Most production workloads        | Balances quality, latency, and cost.            |
| `tokenless-max`         | Difficult or high-value tasks    | May use stronger and more expensive candidates. |
| `tokenless-ultra-saver` | High-volume, cost-sensitive work | Prioritizes lower cost and higher throughput.   |