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
Cerebras Cloud (CS-3 Wafer-Scale Engine)
⏱️Lowest Latency (TTFT)
0.09s P50
Groq Cloud (TTFT P90: 0.12s)
💰Best Price Value
$0.19 / $0.43
DeepInfra (In / Out $/1M)

Blended Pricing Workload Calculator

Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.

Provider & HostHardware StackOutput Speed (TPS)Latency TTFT (P50)Input Price ($/1M)Output Price ($/1M)Cache Read ($/1M)Blended Price ($/1M)SLA
XiaomiOfficial
Cloud TPU / Nvidia H10065 t/s2.74s (3.84s p90)$0.43$0.87$0.043$0.5499.99%
Groq Cloud
Groq LPU v2 (SRAM)273 t/s0.09s (0.12s p90)$0.37$0.74$0.034$0.4699.95%
Cerebras Cloud
CS-3 Wafer-Scale Engine813 t/s0.12s (0.16s p90)$0.39$0.78$0.4999.90%
Together AI
Nvidia H100 SXM598 t/s2.19s (3.01s p90)$0.28$0.61$0.026$0.3699.95%
DeepInfra
Nvidia H100 / L40S85 t/s2.47s (3.43s p90)$0.19$0.43$0.022$0.2599.90%
Fireworks AI
Nvidia B200 / H100124 t/s1.92s (2.6s p90)$0.26$0.57$0.026$0.3499.99%
0 / 4 Models Selected