GoogleAPI Host Benchmarks
Gemini 2.5 Pro — API Providers & Speed Matrix
Compare live throughput, TTFT latency distributions, prompt cache pricing, and hardware stacks across cloud hosting endpoints.
Fastest Provider
1775 t/s
Lowest Latency (TTFT)
0.09s P50
Best Price Value
$0.56 / $5
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
GoogleOfficial | Cloud TPU / Nvidia H100 | 142 t/s | 21.03s (29.44s p90) | $1.25 | $10 | $0.125 | $3.44 | 99.99% |
Groq Cloud | Groq LPU v2 (SRAM) | 596 t/s | 0.09s (0.12s p90) | $1.06 | $8.5 | $0.1 | $2.92 | 99.95% |
Cerebras Cloud | CS-3 Wafer-Scale Engine | 1775 t/s | 0.12s (0.16s p90) | $1.13 | $9 | — | $3.1 | 99.90% |
Together AI | Nvidia H100 SXM5 | 213 t/s | 16.82s (23.13s p90) | $0.81 | $7 | $0.075 | $2.36 | 99.95% |
DeepInfra | Nvidia H100 / L40S | 185 t/s | 18.93s (26.29s p90) | $0.56 | $5 | $0.063 | $1.67 | 99.90% |
Fireworks AI | Nvidia B200 / H100 | 270 t/s | 14.72s (19.98s p90) | $0.75 | $6.5 | $0.075 | $2.19 | 99.99% |