Model Spend Arena2ND ED.
serves endpoints · 2026-10-03

Nebius

Official site · 🇳🇱 Netherlands

Models it serves

6 endpoints, cheapest first. This is the view the model-by-model tables cannot give you: what one provider actually offers, and at what precision.

ModelQuant$/M in$/M outContextUptime 30m
Nemotron 3 Nano 30Bfp8$0.06$0.24262,144100.0%
Gemma 3 27Bfp8$0.10$0.30110,000100.0%
gpt-oss-120bfp4$0.15$0.60131,072100.0%
Kimi K2.7 Codefp4$0.95$4.00262,144—
GLM-5.3fp4$1.40$4.401,024,000100.0%
GLM-5.1fp8$1.40$4.40202,752100.0%