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
03gpt-5.6-terra
Tier S0 ms
P95: 0 ms
04NVIDIA Nemotron Super 49B v1.5
Tier S48 ms
P95: 49 ms
05Qwen3-Coder-30B-A3B-Instruct
Tier S82 ms
P95: 84 ms
06SDXL 1.0
Tier S112 ms
P95: 160 ms
07Meta-Llama-3_3-70B-Instruct
Tier S136 ms
P95: 138 ms
08Qwen2.5-VL-72B-Instruct
Tier S145 ms
P95: 394 ms
09Mistral-Nemo-Instruct-2407
Tier S158 ms
P95: 190 ms
10Mistral-Small-3.2-24B-Instruct-2506
Tier S174 ms
P95: 691 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.