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

Mara

Official site · origin not confirmed

Models it serves

3 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
gpt-oss-120bunknown$0.15$0.75131,072100.0%
MiniMax-M3unknown$0.60$2.401,048,576—
DeepSeek V3.2unknown$3.00$4.5032,768—