GoogleAPI Host Benchmarks
Gemini 3.5 Flash — API Providers & Speed Matrix
Compare live throughput, TTFT latency distributions, prompt cache pricing, and hardware stacks across cloud hosting endpoints.
Fastest Provider
3338 t/s
Lowest Latency (TTFT)
0.09s P50
Best Price Value
$0.68 / $4.5
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
GoogleOfficial | Cloud TPU / Nvidia H100 | 267 t/s | 24.97s (34.96s p90) | $1.5 | $9 | $0.15 | $3.38 | 99.99% |
Groq Cloud | Groq LPU v2 (SRAM) | 1121 t/s | 0.09s (0.12s p90) | $1.27 | $7.65 | $0.12 | $2.87 | 99.95% |
Cerebras Cloud | CS-3 Wafer-Scale Engine | 3338 t/s | 0.12s (0.16s p90) | $1.35 | $8.1 | — | $3.04 | 99.90% |
Together AI | Nvidia H100 SXM5 | 401 t/s | 19.98s (27.47s p90) | $0.98 | $6.3 | $0.09 | $2.31 | 99.95% |
DeepInfra | Nvidia H100 / L40S | 347 t/s | 22.47s (31.21s p90) | $0.68 | $4.5 | $0.075 | $1.64 | 99.90% |
Fireworks AI | Nvidia B200 / H100 | 507 t/s | 17.48s (23.72s p90) | $0.9 | $5.85 | $0.09 | $2.14 | 99.99% |