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
03NVIDIA Nemotron Super 49B v1.5
Tier S51 ms
P95: 57 ms
04Qwen3-Coder-30B-A3B-Instruct
Tier S90 ms
P95: 103 ms
05Mistral-Nemo-Instruct-2407
Tier S100 ms
P95: 322 ms
06SDXL 1.0
Tier S100 ms
P95: 107 ms
07Qwen2.5-VL-72B-Instruct
Tier S130 ms
P95: 1115 ms
08Meta-Llama-3_3-70B-Instruct
Tier S140 ms
P95: 1892 ms
09Mistral-7B-Instruct-v0.3
Tier S165 ms
P95: 197 ms
10Nous Hermes 3 70B
Tier S185 ms
P95: 202 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.