MistralAPI Host BenchmarksEstimated
Mistral Small 4 Non Reasoning — 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
$0.9 / $3
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
MistralOfficial | Cloud TPU / Nvidia H100 | 60 t/s | 800 ms (1.12 s p90) | $2 | $6 | $0.2 | $3 | 99.99% |
| Groq LPU v2 (SRAM) | 252 t/s | 90 ms (120 ms p90) | $1.7 | $5.1 | $0.16 | $2.55 | 99.95% | |
| CS-3 Wafer-Scale Engine | 750 t/s | 120 ms (160 ms p90) | $1.8 | $5.4 | — | $2.7 | 99.90% | |
| Nvidia H100 SXM5 | 90 t/s | 640 ms (880 ms p90) | $1.3 | $4.2 | $0.12 | $2.03 | 99.95% | |
| Nvidia H100 / L40S | 78 t/s | 720 ms (1.00 s p90) | $0.9 | $3 | $0.1 | $1.43 | 99.90% | |
| Nvidia B200 / H100 | 114 t/s | 560 ms (760 ms p90) | $1.2 | $3.9 | $0.12 | $1.88 | 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.