OpenAI compatible API. Attested gateway. Public status.

MoonshotAI: Kimi K2.6 Performance

TrustedRouter performance signals and provider route posture for MoonshotAI: Kimi K2.6.

Verify gateway
1 URLbase_url migration
100smodels and routes
0prompt logs by default

moonshotai/kimi-k2.6

open weights Performance

All models

AI IQ IQ 117 #19 public AI IQ rank for kimi-k2.6
View AI IQ profile

Measured performance

Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), throughput, and success rate for MoonshotAI: Kimi K2.6 — unsupported route and probe-configuration rows are separated from provider downtime, and no prompt or output content is stored.

Providerp50 TTFTp95 TTFTp50 TTFBThroughputUptimeConfig excludedSamples
crusoe 4821 ms 13707 ms 4821 ms 100.00% 6
fireworks 5689 ms 17573 ms 5688 ms 100.00% 33
wafer 5953 ms 17214 ms 5953 ms 82.86% 35
tinfoil 6936 ms 13192 ms 6936 ms 100.00% 42
together 7137 ms 19891 ms 7137 ms 100.00% 15
parasail 7916 ms 7916 ms 7916 ms 100.00% 1
phala 10319 ms 24984 ms 10318 ms 80.00% 5
novita 11093 ms 11093 ms 11093 ms 100.00% 1
deepinfra 0.00% 1 unsupported_route 1
gmi 0.00% 1

Full provider & model leaderboard.

Provider diversity

24 routes.

More routes give the auto router more room to fail over around provider 429 and 5xx responses.

Streaming

Gateway overhead is measured separately.

Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.

Status

Metadata rollups.

Status samples store latency, outcome, provider, model, route, cost, and region metadata only.

Sign in

Choose a sign in method.