MistralAPI Host BenchmarksEstimated
Magistral Small 1.2 — 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
750 t/s
Lowest latency (TTFT)
90 ms P50
Best price
$0.23 / $0.75
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
MistralOfficial | Cloud TPU / Nvidia H100 | 60 t/s | 1.50 s (2.10 s p90) | $0.5 | $1.5 | $0.05 | $0.75 | 99.99% |
| Groq LPU v2 (SRAM) | 252 t/s | 90 ms (120 ms p90) | $0.42 | $1.27 | $0.04 | $0.63 | 99.95% | |
| CS-3 Wafer-Scale Engine | 750 t/s | 120 ms (160 ms p90) | $0.45 | $1.35 | — | $0.68 | 99.90% | |
| Nvidia H100 SXM5 | 90 t/s | 1.20 s (1.65 s p90) | $0.33 | $1.05 | $0.03 | $0.51 | 99.95% | |
| Nvidia H100 / L40S | 78 t/s | 1.35 s (1.88 s p90) | $0.23 | $0.75 | $0.025 | $0.36 | 99.90% | |
| Nvidia B200 / H100 | 114 t/s | 1.05 s (1.42 s p90) | $0.3 | $0.98 | $0.03 | $0.47 | 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.