Your LLM router or classifier, distilled to run on plain CPU.
Stop paying an LLM to pick from a list.
Send us examples of the decisions your LLM makes. Get back a small model that makes the same calls on any CPU, for a fraction of the cost. It's yours to keep.
Free report in about a minute · No account · $99 only if you keep the model
Upload examples
Past questions and the answer your LLM gave. One file, no account.
See your savings
In about a minute: how much of your traffic a CPU model can take, and what that saves you.
Keep the model
$99, once. Runs on your servers, even offline. Anything it isn't sure about goes to your LLM.
- Used only to build your model. Never shared, never used to train anything else.
- Deleted within 24 hours. Or the moment you click "Delete my data now".
- The model runs on your machines. No calls home, no lock-in.
Free audit
- Up to 10,000 rows per upload
- How much traffic the CPU model takes at 90%, 95% and 99% accuracy
- Savings calculator at your price per call
- 3 reports a day, no account
One model
- Download the model and the script that runs it
- Runs offline on any CPU
- Standard formats, no lock-in, yours forever
- Buy it from your report page, after you've seen the numbers
Continuous factory
Coming soon
- Unlimited models
- Retrained and re-checked as your traffic changes
- New versions delivered to your registry
One email when it opens. No marketing, no sharing with third parties.
What kinds of decisions work?
Routing, intent and category labels, allow/deny checks and triage: anything with a fixed list of 2 to about 100 answers. If yours isn't a fit, the free report says so.
What happens to my data?
It trains only your model and is deleted 24 hours after upload (24 hours after purchase, so you have time to download). "Delete my data now" on your report removes it at once.
Am I locked in?
No. You download the model and a small script that runs it, using open-source libraries only. It runs offline, forever.
What does it need to run?
An ordinary CPU. No GPU, and a few milliseconds per decision.
Technical details: the benchmark, the download, the log converter →