MoonshotAI: Kimi K2.7 Code Performance
Try Kimi K2.7 Code on us. Starter credit covers your first requests, then one key reaches all 14 provider routes with automatic failover.
moonshotai/kimi-k2.7-code
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), effective throughput, and success rate for MoonshotAI: Kimi K2.7 Code. 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 |
|---|---|---|---|---|---|---|
| azure | 1617 ms | 1617 ms | 94 tok/s n=1 | 100.00% | — | 1 |
| wandb | 1678 ms | 2882 ms | 62 tok/s n=2 | 100.00% | — | 3 |
| siliconflow | 1786 ms | 2939 ms | 63 tok/s n=2 | 100.00% | — | 3 |
| featherless | 2185 ms | 2185 ms | 75 tok/s n=2 | 100.00% | — | 1 |
| cloudflare-workers-ai | 2460 ms | 2460 ms | 72 tok/s n=2 | 100.00% | — | 1 |
| kimi | 2482 ms | 12212 ms | 41 tok/s n=2 | 100.00% | — | 9 |
| streamlake | 2900 ms | 2900 ms | 44 tok/s n=2 | 100.00% | — | 1 |
| alibaba | — | — | 60 tok/s n=2 | — | — | 0 |
| atlas-cloud | — | — | 72 tok/s n=2 | — | — | 0 |
| inceptron | — | — | — | — | 4 insufficient_quota |
0 |
| io-net | — | — | 123 tok/s n=2 | — | — | 0 |
| lyceum | — | — | 167 tok/s n=2 | — | — | 0 |
| novita | — | — | 62 tok/s n=2 | — | — | 0 |
| tencent | — | — | 38 tok/s n=2 | — | — | 0 |
Full provider & model leaderboard.
14 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.