MoonshotAI: Kimi K3 Performance
TrustedRouter performance signals and provider route posture for MoonshotAI: Kimi K3.
moonshotai/kimi-k3
Measured performance
Continuously sampled p50/p95 time-to-first-token (TTFT), time-to-first-byte (TTFB), effective throughput, and success rate for MoonshotAI: Kimi K3. 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 |
|---|---|---|---|---|---|---|---|
| together | 1533 ms | 5653 ms | 1533 ms | 39 tok/s n=2 | 100.00% | — | 4 |
| baseten | 2117 ms | 3800 ms | 2117 ms | 81 tok/s n=2 | 100.00% | 1 router_error |
8 |
| cloudflare-workers-ai | 2269 ms | 5087 ms | 2269 ms | 25 tok/s n=1 | 100.00% | — | 2 |
| telnyx | 2582 ms | 6342 ms | 2581 ms | 46 tok/s n=2 | 100.00% | — | 6 |
| kimi | 3516 ms | 5564 ms | 3515 ms | 32 tok/s n=1 | 100.00% | — | 4 |
| fireworks | 3928 ms | 16568 ms | 3927 ms | 36 tok/s n=2 | 100.00% | — | 7 |
| novita | 4000 ms | 19657 ms | 4000 ms | 24 tok/s n=2 | 100.00% | — | 2 |
| gmi | 5685 ms | 7435 ms | 5685 ms | 21 tok/s n=2 | 100.00% | — | 11 |
| phala | 3107 ms | 19836 ms | 3107 ms | 30 tok/s n=1 | 96.15% | — | 26 |
| siliconflow | 4012 ms | 5081 ms | 4012 ms | 24 tok/s n=2 | 75.00% | — | 4 |
| atlas-cloud | — | — | — | 21 tok/s n=2 | — | — | 0 |
| nebius | — | — | — | 65 tok/s n=1 | — | — | 0 |
Full provider & model leaderboard.
24 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.