Empire Gateway features

Every shipping feature, mapped to what we use in production.

Feature matrix

12-model fallback cascade

Free Groq → Cerebras → Gemini Flash → CF AI Workers → paid GPT-4o / Claude / etc. Picks cheapest meeting latency+quality SLA.

OpenAI-compatible drop-in

Set base_url to our gateway. Existing OpenAI SDK code keeps working.

Cost-per-call routing

Configure per-route policies: latency-first / cost-first / quality-first.

Hash-chained audit log

Every request signed, queryable, exportable for SOC2 path.

Per-tenant rate-limits

Free 1k req/mo, Indie 100k, Pro 1M, Enterprise SLA.

Private deploy option

Enterprise: ship the gateway in your VPC. Same code.

See pricing → See how we compare