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
Cerebras Cloud (CS-3 Wafer-Scale Engine)
⏱️Lowest Latency (TTFT)
0.09s P50
Groq Cloud (TTFT P90: 0.12s)
💰Best Price Value
$0.03 / $0.15
DeepInfra (In / Out $/1M)

Blended Pricing Workload Calculator

Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.

Provider & HostHardware StackOutput Speed (TPS)Latency TTFT (P50)Input Price ($/1M)Output Price ($/1M)Cache Read ($/1M)Blended Price ($/1M)SLA
GoogleOfficial
Cloud TPU / Nvidia H10035 t/s1.1s (1.54s p90)$0.075$0.3$0.007$0.1399.99%
Groq Cloud
Groq LPU v2 (SRAM)147 t/s0.09s (0.12s p90)$0.06$0.26$0.006$0.1199.95%
Cerebras Cloud
CS-3 Wafer-Scale Engine438 t/s0.12s (0.16s p90)$0.07$0.27$0.1299.90%
Together AI
Nvidia H100 SXM553 t/s0.88s (1.21s p90)$0.05$0.21$0.004$0.0999.95%
DeepInfra
Nvidia H100 / L40S46 t/s0.99s (1.38s p90)$0.03$0.15$0.004$0.0699.90%
Fireworks AI
Nvidia B200 / H10067 t/s0.77s (1.04s p90)$0.04$0.2$0.004$0.0899.99%
0 / 4 Models Selected