Routing modes

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.

⌘I