NVIDIAAPI Host BenchmarksEstimated
NVIDIA Nemotron 3.5 Super-VL — API Providers & Speed Matrix
Modelled throughput, TTFT latency and prompt-cache pricing estimates across cloud hosting endpoints, derived from official list prices and public benchmarks.
Fastest provider
1375 t/s
Lowest latency (TTFT)
90 ms P50
Best price
$0.16 / $0.6
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
NVIDIAOfficial | Cloud TPU / Nvidia H100 | 110 t/s | 800 ms (1.12 s p90) | $0.35 | $1.2 | $0.035 | $0.56 | 99.99% |
| Groq LPU v2 (SRAM) | 462 t/s | 90 ms (120 ms p90) | $0.3 | $1.02 | $0.028 | $0.48 | 99.95% | |
| CS-3 Wafer-Scale Engine | 1375 t/s | 120 ms (160 ms p90) | $0.32 | $1.08 | — | $0.51 | 99.90% | |
| Nvidia H100 SXM5 | 165 t/s | 640 ms (880 ms p90) | $0.23 | $0.84 | $0.021 | $0.38 | 99.95% | |
| Nvidia H100 / L40S | 143 t/s | 720 ms (1.00 s p90) | $0.16 | $0.6 | $0.017 | $0.27 | 99.90% | |
| Nvidia B200 / H100 | 209 t/s | 560 ms (760 ms p90) | $0.21 | $0.78 | $0.021 | $0.35 | 99.99% |
Figures are modelled estimates based on published list prices and public throughput benchmarks — not measured on live endpoints. Verify current pricing and terms with each host before committing.