Pricing
Local, in-browser inference is the default — and it’s free, because the visitor’s device does the work. You pay only when you need hosted remote inference and higher limits.
| Free | Starter | Pro | Enterprise | |
|---|---|---|---|---|
| Price | $0 | $19/mo | $99/mo | Custom |
| Local (in-browser) inference | ✅ | ✅ | ✅ | ✅ |
| Remote inference (fallback) | — | ✅ | ✅ | ✅ |
| Included remote tokens / mo | 0 | 500K | 5M | Custom |
| Domains per key | 1 | 5 | 20 | Unlimited |
| Bring your own key (BYOK) | — | — | ✅ | ✅ |
| Remove “Powered by InferKit” | — | — | ✅ | ✅ |
| Bot protection (Turnstile) | — | ✅ | ✅ | ✅ |
| Team & roles (RBAC) | ✅ | ✅ | ✅ | ✅ |
| Support | Community | Priority | SLA + dedicated | |
| SSO / audit logs / dedicated infra | — | — | — | ✅ |
* Remote usage beyond the included allowance is billed as overage. With BYOK (Pro/Enterprise), remote tokens are billed by your provider; InferKit charges only the platform fee.
Which tier?
- Free — hobby projects, blogs, docs, evaluation. Local-only; visitors need WebGPU.
- Starter — production sites that want a remote fallback for every visitor.
- Pro — growing products, agencies, and teams wanting BYOK + white-label.
- Enterprise — SSO, audit logs, dedicated infrastructure, custom SLAs.
Upgrade, downgrade, or cancel anytime from Dashboard → Billing (self-serve via Stripe). Talk to us about Enterprise: [email protected].