MoonshotAI: Kimi K2.6 Performance
Try Kimi K2.6 on us. Starter credit covers your first requests, then one key reaches all 17 provider routes with automatic failover.
moonshotai/kimi-k2.6
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for MoonshotAI: Kimi K2.6. 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 |
|---|---|---|---|---|---|---|
| kimi | 1889 ms | 2714 ms | 38 tok/s n=2 | 100.00% | 1 provider_error |
11 |
| azure | 1122 ms | 1122 ms | 98 tok/s n=2 | 100.00% | — | 1 |
| digitalocean | 1146 ms | 2787 ms | 32 tok/s n=2 | 100.00% | — | 2 |
| siliconflow | 1192 ms | 1356 ms | 28 tok/s n=2 | 100.00% | — | 2 |
| io-net | 1404 ms | 1524 ms | 71 tok/s n=2 | 100.00% | — | 2 |
| sail-research | 1577 ms | 1735 ms | 71 tok/s n=2 | 100.00% | — | 5 |
| streamlake | 2558 ms | 2682 ms | 43 tok/s n=2 | 100.00% | — | 2 |
| wandb | 2898 ms | 2898 ms | 194 tok/s n=2 | 100.00% | — | 1 |
| cloudflare-workers-ai | 3125 ms | 3125 ms | 43 tok/s n=2 | 100.00% | — | 1 |
| parasail | 3269 ms | 3269 ms | 98 tok/s n=1 | 100.00% | — | 1 |
| deepinfra | 4154 ms | 4154 ms | 102 tok/s n=1 | 100.00% | — | 1 |
| atlas-cloud | — | — | 75 tok/s n=2 | — | — | 0 |
| chutes | — | — | 28 tok/s n=2 | — | — | 0 |
| featherless | — | — | 27 tok/s n=2 | — | — | 0 |
| inceptron | — | — | — | — | 6 insufficient_quota |
0 |
| novita | — | — | 35 tok/s n=2 | — | — | 0 |
| telnyx | — | — | 75 tok/s n=2 | — | — | 0 |
Full provider & model leaderboard.
17 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.