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

Relace

Official site · origin not confirmed

Models it serves

7 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
GLM-5.3-Flashunknown$0.04$0.501,048,57699.2%
DeepSeek V4.1 Flashunknown$0.02$0.601,048,57699.9%
DeepSeek V4 Flashfp4$0.01$1.281,048,57698.9%
GLM-5.2unknown$0.10$4.001,048,576100.0%
GLM-5.3unknown$0.12$4.001,048,576100.0%
DeepSeek V4 Profp4$0.90$2.701,048,576100.0%
Kimi K3fp4$0.99$13.001,048,576100.0%