GoogleAPI Host Benchmarks
Gemma 4 31B — API Providers & Speed Matrix
Compare live throughput, TTFT latency distributions, prompt cache pricing, and hardware stacks across cloud hosting endpoints.
Fastest Provider
438 t/s
Lowest Latency (TTFT)
0.09s P50
Best Price Value
$0.03 / $0.15
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
GoogleOfficial | Cloud TPU / Nvidia H100 | 35 t/s | 1.1s (1.54s p90) | $0.075 | $0.3 | $0.007 | $0.13 | 99.99% |
Groq Cloud | Groq LPU v2 (SRAM) | 147 t/s | 0.09s (0.12s p90) | $0.06 | $0.26 | $0.006 | $0.11 | 99.95% |
Cerebras Cloud | CS-3 Wafer-Scale Engine | 438 t/s | 0.12s (0.16s p90) | $0.07 | $0.27 | — | $0.12 | 99.90% |
Together AI | Nvidia H100 SXM5 | 53 t/s | 0.88s (1.21s p90) | $0.05 | $0.21 | $0.004 | $0.09 | 99.95% |
DeepInfra | Nvidia H100 / L40S | 46 t/s | 0.99s (1.38s p90) | $0.03 | $0.15 | $0.004 | $0.06 | 99.90% |
Fireworks AI | Nvidia B200 / H100 | 67 t/s | 0.77s (1.04s p90) | $0.04 | $0.2 | $0.004 | $0.08 | 99.99% |