AnthropicAPI Host Benchmarks
Claude Opus 5 — API Providers & Speed Matrix
Compare live throughput, TTFT latency distributions, prompt cache pricing, and hardware stacks across cloud hosting endpoints.
Fastest Provider
750 t/s
Lowest Latency (TTFT)
0.09s P50
Best Price Value
$2.25 / $12.5
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
AnthropicOfficial | Cloud TPU / Nvidia H100 | 60 t/s | 69.32s (97.05s p90) | $5 | $25 | $0.5 | $10 | 99.99% |
Groq Cloud | Groq LPU v2 (SRAM) | 252 t/s | 0.09s (0.12s p90) | $4.25 | $21.25 | $0.4 | $8.5 | 99.95% |
Cerebras Cloud | CS-3 Wafer-Scale Engine | 750 t/s | 0.12s (0.16s p90) | $4.5 | $22.5 | — | $9 | 99.90% |
Together AI | Nvidia H100 SXM5 | 90 t/s | 55.46s (76.25s p90) | $3.25 | $17.5 | $0.3 | $6.81 | 99.95% |
DeepInfra | Nvidia H100 / L40S | 78 t/s | 62.39s (86.65s p90) | $2.25 | $12.5 | $0.25 | $4.81 | 99.90% |
Fireworks AI | Nvidia B200 / H100 | 114 t/s | 48.52s (65.85s p90) | $3 | $16.25 | $0.3 | $6.31 | 99.99% |