MicrosoftAPI Host Benchmarks
Phi 4 — API Providers & Speed Matrix
Compare live throughput, TTFT latency distributions, prompt cache pricing, and hardware stacks across cloud hosting endpoints.
Fastest Provider
750 t/s
Lowest Latency (TTFT)
0.09s P50
Best Price Value
$0.07 / $0.3
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
MicrosoftOfficial | Cloud TPU / Nvidia H100 | 60 t/s | 0.8s (1.12s p90) | $0.15 | $0.6 | $0.015 | $0.26 | 99.99% |
Groq Cloud | Groq LPU v2 (SRAM) | 252 t/s | 0.09s (0.12s p90) | $0.13 | $0.51 | $0.012 | $0.23 | 99.95% |
Cerebras Cloud | CS-3 Wafer-Scale Engine | 750 t/s | 0.12s (0.16s p90) | $0.14 | $0.54 | — | $0.24 | 99.90% |
Together AI | Nvidia H100 SXM5 | 90 t/s | 0.64s (0.88s p90) | $0.1 | $0.42 | $0.009 | $0.18 | 99.95% |
DeepInfra | Nvidia H100 / L40S | 78 t/s | 0.72s (1s p90) | $0.07 | $0.3 | $0.007 | $0.13 | 99.90% |
Fireworks AI | Nvidia B200 / H100 | 114 t/s | 0.56s (0.76s p90) | $0.09 | $0.39 | $0.009 | $0.17 | 99.99% |