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

ModelRun

Official site · origin not confirmed

Models it serves

2 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
Gemma 4 31Bfp4$0.75$1.00262,14499.7%
MiniMax-M3fp4$0.75$3.001,048,57695.3%