OpenAI compatible API. Attested gateway. Public status.
MoonshotAI: Kimi K2.5 Performance
TrustedRouter performance signals and provider route posture for MoonshotAI: Kimi K2.5.
1 URLbase_url migration
100smodels and routes
0prompt logs by default
moonshotai/kimi-k2.5
open weights
Performance
AI IQ
IQ 109
#29 public AI IQ rank for kimi-k2.5
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 K2.5 — 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 |
|---|---|---|---|---|---|---|---|
| fireworks | 4665 ms | 23664 ms | 4664 ms | — | 100.00% | — | 12 |
| kimi | 5772 ms | 17457 ms | 5771 ms | — | 100.00% | — | 133 |
| baseten | 9280 ms | 21108 ms | 9279 ms | — | 100.00% | — | 19 |
| novita | 10409 ms | 10409 ms | 10408 ms | — | 100.00% | — | 1 |
| phala | 11252 ms | 27880 ms | 11251 ms | — | 79.17% | — | 24 |
Full provider & model leaderboard.
Provider diversity
11 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.