Demo mode — sample data. Editing is disabled.
Access the real dealRoute each request to the best model for the job with mizan/auto.
Auto-routing savings
What auto-routed calls actually cost, versus what the same traffic would have cost on a few reference models.
$1.91
spent in this period across 294 auto-routed requests
$1.55 saved versus routing everything to GPT-5.6 Sol
If always Claude Sonnet 5
$1.73
If always GPT-5.6 Sol
$3.46
If always Grok 4.6
$2.56
Auto Router
Route to the best model for each request using mizan/auto. When enabled, every call to mizan/auto is classified, ranked against your task's top models, and routed — always billed from your wallet.
Model patterns to filter which models auto-routing can route between. Separate patterns with commas or newlines. Supports wildcards (e.g., anthropic/* matches all Anthropic models). Leave empty to use all supported models.
157 models matched
0 = pure quality (best model regardless of cost), 10 = cheapest model wins. Intermediate values blend quality and cost signals.
Once a model is picked for a conversation, keep using it for up to 5 minutes of inactivity — skips reclassification on every message and keeps that conversation's prompt-cache streak intact, even if a later message would classify differently.
Prevent overrides. Ignore per-request plugins settings from your code and always use these account defaults.
Savings
What auto-routing would have cost on the most expensive eligible model, versus what it actually cost — per month.
$1.87
total saved
| Month | Requests | Actual spend | Premium baseline | Saved |
|---|---|---|---|---|
| August 2026 | 221 | $1.43 | $2.71 | $1.28 |
| September 2026 | 73 | $0.48 | $1.08 | $0.60 |