XiaomiAPI Host Benchmarks
MiMo V2.5 Pro — API Providers & Speed Matrix
Compare live throughput, TTFT latency distributions, prompt cache pricing, and hardware stacks across cloud hosting endpoints.
Fastest Provider
813 t/s
Lowest Latency (TTFT)
0.09s P50
Best Price Value
$0.19 / $0.43
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
XiaomiOfficial | Cloud TPU / Nvidia H100 | 65 t/s | 2.74s (3.84s p90) | $0.43 | $0.87 | $0.043 | $0.54 | 99.99% |
Groq Cloud | Groq LPU v2 (SRAM) | 273 t/s | 0.09s (0.12s p90) | $0.37 | $0.74 | $0.034 | $0.46 | 99.95% |
Cerebras Cloud | CS-3 Wafer-Scale Engine | 813 t/s | 0.12s (0.16s p90) | $0.39 | $0.78 | — | $0.49 | 99.90% |
Together AI | Nvidia H100 SXM5 | 98 t/s | 2.19s (3.01s p90) | $0.28 | $0.61 | $0.026 | $0.36 | 99.95% |
DeepInfra | Nvidia H100 / L40S | 85 t/s | 2.47s (3.43s p90) | $0.19 | $0.43 | $0.022 | $0.25 | 99.90% |
Fireworks AI | Nvidia B200 / H100 | 124 t/s | 1.92s (2.6s p90) | $0.26 | $0.57 | $0.026 | $0.34 | 99.99% |