Skip to content

Performance

See identical-hardware benchmarks for Sluis, LiteLLM, and Bifrost, including gateway overhead, throughput, tail latency, and live-model methodology.

One upstream. Identical hardware. The same load.

Every gateway fronts the same keep-alive mock at the same concurrency, isolating gateway overhead from provider variance. The run exercises the OpenAI protocol path; the Anthropic surface adds one translation step on top.

One shared mock upstream

All four gateways hit the same Node mock: keep-alive on, one fixed 60 ms delay.

Isolated, identical hardware

Each runs in a CPU/memory-pinned container, hit by oha at 256 connections.

Gate-off baseline

Allow-all policy, DLP observe-only, audit content off: Sluis as a plain OpenAI-compatible proxy.

Gate-on: the real product

EU residency, DLP masking, content retention, hash-chained audit: every gate on the hot path.

The numbers, exactly as measured.

Two Sluis columns: gate-off, an apples-to-apples proxy comparison; gate-on, the compliance overhead against our own baseline.

2026-07-04 · oha 1.14 · c=256 · 30 s

MetricSluis gate-offSluis gate-onLiteLLMBifrost
Throughput (RPS)4,0463,6782983,148
p50 latency (ms)626374380
p99 latency (ms)771304,584118
Peak RSS (MiB)TBDTBDTBDTBD
Success rate100%100%100%100%

Latency is end-to-end through the gateway over the shared fixed-latency mock: the differences are the gateways' own overhead.

The gate-on column is compliance overhead versus gate-off, not a head-to-head.

Against a live model (rate-capped at 10 RPS so the provider never throttles), the gate adds nothing at the median: 305 ms gate-on versus 304 ms gate-off. The p99 tails in that lane belong to the provider, not the gateways.

An honest claim, or none at all.

A benchmark you can't trust is worse than none, so we set the rules before any number ships.

  • The head-to-head “fastest” claim is gate-off only: Sluis as a plain proxy versus LiteLLM and Bifrost.
  • Gate-on is overhead against our own baseline: one millisecond at the median, nine percent throughput, p99 130 ms versus 77 ms.
  • The rate-capped live lane adds nothing at the median; its p99 tails are provider variance.
  • If gate-off Sluis isn't clearly faster, the headline becomes “compliance at negligible cost”.