OpenAI compatible API. Attested gateway. Public status.
MoonshotAI: Kimi K2.6 Performance
TrustedRouter performance signals and provider route posture for MoonshotAI: Kimi K2.6.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
moonshotai/kimi-k2.6
Performance
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.
| Provider | p50 TTFT | p95 TTFT | p50 TTFB | Throughput | Uptime | Config excluded | Samples |
|---|---|---|---|---|---|---|---|
| together | 1278 ms | 5495 ms | 1176 ms | — | 97.03% | — | 101 |
| tinfoil | 1399 ms | 2938 ms | 1368 ms | — | 100.00% | — | 60 |
| phala | 1694 ms | 7563 ms | 1691 ms | — | 100.00% | — | 19 |
| novita | 1801 ms | 2340 ms | 1800 ms | — | 100.00% | — | 5 |
| parasail | 2097 ms | 7775 ms | 1993 ms | — | 57.14% | — | 14 |
| kimi | 2206 ms | 3771 ms | 2123 ms | — | 96.62% | — | 148 |
Full provider & model leaderboard.
Provider diversity
12 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.
View public status or inspect provider routes.