Benchmarks

Speed test

P50 = median response time for a standard 500-token output. Measured from EU (Amsterdam). P95 = tail latency — 95% of requests complete within this time. Three runs per model per test cycle; values are medians across cycles.

Tier S< 200 ms
Tier A< 500 ms
Tier B< 1000 ms
Tier C> 1000 ms
P50 (median)P95 (tail)
01FLUX.1 Kontext [max] — Multi-Image Fusion
Tier S0 ms
P95: 0 ms
02FLUX.1 Kontext [pro] — Multi-Image Fusion
Tier S0 ms
P95: 0 ms
03Whisper Large v3 Turbo (speech-to-text)
Tier S21 ms
P95: 26 ms
04NVIDIA Nemotron Super 49B v1.5
Tier S48 ms
P95: 49 ms
05SDXL 1.0
Tier S112 ms
P95: 160 ms
06Qwen2.5-VL-72B-Instruct
Tier S143 ms
P95: 145 ms
07Mistral Voxtral Small 24B
Tier A205 ms
P95: 256 ms
08Nous Hermes 3 70B
Tier A212 ms
P95: 883 ms
09DeepSeek v3.2
Tier A219 ms
P95: 680 ms
10Llama 3.3 70B Instruct
Tier A243 ms
P95: 252 ms
How we measure: Each model receives an identical prompt targeting a ~500-token output. We run 3 sequential calls per test cycle and compute P50/P95 across the distribution. Tests run 4× per day from a single EU endpoint. Network overhead is included.