MoonshotAI: Kimi K3.1 Pro Performance
Try Kimi K3.1 Pro on us. Starter credit covers your first requests, then one key reaches all 15 provider routes with automatic failover.
moonshotai/kimi-k3.1-pro
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for MoonshotAI: Kimi K3.1 Pro. 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 | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| telnyx | 594 ms | 704 ms | — | 100.00% | — | 2 |
| sail-research | 760 ms | 1561 ms | — | 100.00% | — | 2 |
| boundless | 762 ms | 2511 ms | — | 100.00% | — | 2 |
| nebius | 1174 ms | 1174 ms | — | 100.00% | — | 2 |
| baseten | 1210 ms | 1905 ms | — | 100.00% | — | 3 |
| engy | 1508 ms | 1508 ms | — | 100.00% | — | 1 |
| tinfoil | 1796 ms | 1796 ms | — | 100.00% | — | 3 |
| kimi | 1935 ms | 5476 ms | — | 100.00% | — | 5 |
| arcee | 3346 ms | 3346 ms | — | 100.00% | — | 1 |
| lyceum | — | — | — | — | 7 unsupported_route |
0 |
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.