GoogleAPI Host Benchmarks
Gemini 3.6 Flash — API Providers & Speed Matrix
Compare live throughput, TTFT latency distributions, prompt cache pricing, and hardware stacks across cloud hosting endpoints.
Fastest Provider
2913 t/s
Lowest Latency (TTFT)
0.09s P50
Best Price Value
$0.68 / $3.75
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
GoogleOfficial | Cloud TPU / Nvidia H100 | 233 t/s | 15.67s (21.94s p90) | $1.5 | $7.5 | $0.15 | $3 | 99.99% |
Groq Cloud | Groq LPU v2 (SRAM) | 979 t/s | 0.09s (0.12s p90) | $1.27 | $6.38 | $0.12 | $2.55 | 99.95% |
Cerebras Cloud | CS-3 Wafer-Scale Engine | 2913 t/s | 0.12s (0.16s p90) | $1.35 | $6.75 | — | $2.7 | 99.90% |
Together AI | Nvidia H100 SXM5 | 350 t/s | 12.54s (17.24s p90) | $0.98 | $5.25 | $0.09 | $2.05 | 99.95% |
DeepInfra | Nvidia H100 / L40S | 303 t/s | 14.1s (19.59s p90) | $0.68 | $3.75 | $0.075 | $1.45 | 99.90% |
Fireworks AI | Nvidia B200 / H100 | 443 t/s | 10.97s (14.89s p90) | $0.9 | $4.88 | $0.09 | $1.9 | 99.99% |