OpenAIAPI Host Benchmarks
GPT-oss-120B — API Providers & Speed Matrix
Compare live throughput, TTFT latency distributions, prompt cache pricing, and hardware stacks across cloud hosting endpoints.
Fastest Provider
3000 t/s
Lowest Latency (TTFT)
0.09s P50
Best Price Value
$0.05 / $0.2
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
OpenAIOfficial | Cloud TPU / Nvidia H100 | 240 t/s | 0.8s (1.12s p90) | $0.1 | $0.4 | $0.01 | $0.18 | 99.99% |
Groq Cloud | Groq LPU v2 (SRAM) | 1008 t/s | 0.09s (0.12s p90) | $0.09 | $0.34 | $0.008 | $0.15 | 99.95% |
Cerebras Cloud | CS-3 Wafer-Scale Engine | 3000 t/s | 0.12s (0.16s p90) | $0.09 | $0.36 | — | $0.16 | 99.90% |
Together AI | Nvidia H100 SXM5 | 360 t/s | 0.64s (0.88s p90) | $0.07 | $0.28 | $0.006 | $0.12 | 99.95% |
DeepInfra | Nvidia H100 / L40S | 312 t/s | 0.72s (1s p90) | $0.05 | $0.2 | $0.005 | $0.09 | 99.90% |
Fireworks AI | Nvidia B200 / H100 | 456 t/s | 0.56s (0.76s p90) | $0.06 | $0.26 | $0.006 | $0.11 | 99.99% |