AnthropicAPI Host Benchmarks
Claude Mythos 5 — API Providers & Speed Matrix
Compare live throughput, TTFT latency distributions, prompt cache pricing, and hardware stacks across cloud hosting endpoints.
Fastest Provider
625 t/s
Lowest Latency (TTFT)
0.09s P50
Best Price Value
$4.5 / $25
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
AnthropicOfficial | Cloud TPU / Nvidia H100 | 50 t/s | 0.8s (1.12s p90) | $10 | $50 | $1 | $20 | 99.99% |
Groq Cloud | Groq LPU v2 (SRAM) | 210 t/s | 0.09s (0.12s p90) | $8.5 | $42.5 | $0.8 | $17 | 99.95% |
Cerebras Cloud | CS-3 Wafer-Scale Engine | 625 t/s | 0.12s (0.16s p90) | $9 | $45 | — | $18 | 99.90% |
Together AI | Nvidia H100 SXM5 | 75 t/s | 0.64s (0.88s p90) | $6.5 | $35 | $0.6 | $13.63 | 99.95% |
DeepInfra | Nvidia H100 / L40S | 65 t/s | 0.72s (1s p90) | $4.5 | $25 | $0.5 | $9.63 | 99.90% |
Fireworks AI | Nvidia B200 / H100 | 95 t/s | 0.56s (0.76s p90) | $6 | $32.5 | $0.6 | $12.63 | 99.99% |