Model Spend Arena2ND ED.
serves endpoints · 2026-08-14

Sail Research

origin not confirmed

Models it serves

4 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
DeepSeek V4 Flashfp4$0.09$0.18262,14499.4%
GLM-5.2fp8$0.50$3.151,048,57699.6%
Kimi K2.6int4$1.00$4.00262,144100.0%
Kimi K3fp4$3.00$15.00974,84299.6%
◆ Some links on this page are referral links: if you sign up through them this site may earn a commission, at no extra cost to you. Rankings, prices and measurements are taken from the sources listed under Method, and are not influenced by whether a provider has a referral programme.