MoonshotAI: Kimi K2.5 Performance
TrustedRouter performance signals and provider route posture for MoonshotAI: Kimi K2.5.
moonshotai/kimi-k2.5
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate for MoonshotAI: Kimi K2.5. Effective throughput uses provider-reported output tokens over complete request time. 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 | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|---|
| novita | 1243 ms | 1243 ms | 1243 ms | — | 100.00% | — | 1 |
| digitalocean | 1572 ms | 7628 ms | 1572 ms | — | 100.00% | — | 5 |
| kimi | 1945 ms | 4050 ms | 1945 ms | — | 100.00% | — | 7 |
| deepinfra | 2274 ms | 4701 ms | 2274 ms | — | 100.00% | — | 4 |
| telnyx | 2335 ms | 3886 ms | 2335 ms | — | 100.00% | 2 probe_config_error |
5 |
| atlas-cloud | 2599 ms | 2599 ms | 2599 ms | — | 100.00% | — | 1 |
| alibaba | 2959 ms | 3334 ms | 2959 ms | — | 100.00% | — | 2 |
Full provider & model leaderboard.
15 routes.
More routes give the auto router more room to fail over around provider 429 and 5xx responses.
Gateway overhead is measured separately.
Public status separates TLS/health overhead from full model latency so slow LLMs do not inflate the router metric.
Metadata rollups.
Status samples store latency, outcome, provider, model, route, cost, and region metadata only.
View public status or inspect provider routes.