Moonshot AIAPI Host Benchmarks
Kimi K3 — API Providers & Speed Matrix
Compare live throughput, TTFT latency distributions, prompt cache pricing, and hardware stacks across cloud hosting endpoints.
Fastest Provider
463 t/s
Lowest Latency (TTFT)
0.09s P50
Best Price Value
$1.35 / $7.5
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
Moonshot AIOfficial | Cloud TPU / Nvidia H100 | 37 t/s | 3.06s (4.28s p90) | $3 | $15 | $0.3 | $6 | 99.99% |
Groq Cloud | Groq LPU v2 (SRAM) | 155 t/s | 0.09s (0.12s p90) | $2.55 | $12.75 | $0.24 | $5.1 | 99.95% |
Cerebras Cloud | CS-3 Wafer-Scale Engine | 463 t/s | 0.12s (0.16s p90) | $2.7 | $13.5 | — | $5.4 | 99.90% |
Together AI | Nvidia H100 SXM5 | 56 t/s | 2.45s (3.37s p90) | $1.95 | $10.5 | $0.18 | $4.09 | 99.95% |
DeepInfra | Nvidia H100 / L40S | 48 t/s | 2.75s (3.83s p90) | $1.35 | $7.5 | $0.15 | $2.89 | 99.90% |
Fireworks AI | Nvidia B200 / H100 | 70 t/s | 2.14s (2.91s p90) | $1.8 | $9.75 | $0.18 | $3.79 | 99.99% |