MiniMaxAPI Host Benchmarks
MiniMax M3 — API Providers & Speed Matrix
Compare live throughput, TTFT latency distributions, prompt cache pricing, and hardware stacks across cloud hosting endpoints.
Fastest Provider
1163 t/s
Lowest Latency (TTFT)
0.09s P50
Best Price Value
$0.14 / $0.6
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
MiniMaxOfficial | Cloud TPU / Nvidia H100 | 93 t/s | 1.55s (2.17s p90) | $0.3 | $1.2 | $0.03 | $0.52 | 99.99% |
Groq Cloud | Groq LPU v2 (SRAM) | 391 t/s | 0.09s (0.12s p90) | $0.26 | $1.02 | $0.024 | $0.45 | 99.95% |
Cerebras Cloud | CS-3 Wafer-Scale Engine | 1163 t/s | 0.12s (0.16s p90) | $0.27 | $1.08 | — | $0.47 | 99.90% |
Together AI | Nvidia H100 SXM5 | 140 t/s | 1.24s (1.71s p90) | $0.2 | $0.84 | $0.018 | $0.36 | 99.95% |
DeepInfra | Nvidia H100 / L40S | 121 t/s | 1.4s (1.94s p90) | $0.14 | $0.6 | $0.015 | $0.26 | 99.90% |
Fireworks AI | Nvidia B200 / H100 | 177 t/s | 1.08s (1.47s p90) | $0.18 | $0.78 | $0.018 | $0.33 | 99.99% |