InferKit Documentation
Everything you need to ship private, on-device AI chat — from a one-tag install to server-side integration. Start with the Quickstart, then dig into the reference.
Overview
What InferKit is, how local vs remote inference works, and when to use each.
Quickstart
Add the widget to any page in a few minutes — script tag to first answer.
API & SDK Reference
The SDK init options and the Platform API for advanced / server-side use.
Security & Privacy
On-device processing, data handling, key fencing, and abuse protection.
Pricing
Free local inference, paid remote fallback, BYOK, and overage details.
FAQ
Common questions on browsers, model size, grounding, billing, and support.
Error Reference
The stable error envelope and full code catalog for branching + support.