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

Wafer

Official site · origin not confirmed

Models it serves

10 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 V4.1 Flashunknown$0.05$0.601,048,576100.0%
GLM-5.3-Flashunknown$0.10$0.501,048,57699.9%
DeepSeek V4 Flashunknown$0.12$0.701,048,576100.0%
GLM-5.3unknown$0.22$3.391,048,576100.0%
GLM-5.3unknown$0.22$3.391,048,576100.0%
Qwen3.8-27Bunknown$0.02$4.35262,144100.0%
DeepSeek V4 Prounknown$0.33$4.201,048,576100.0%
GLM-5.2unknown$0.41$3.991,048,57699.9%
Kimi K3unknown$1.44$14.001,048,576100.0%
Kimi K3unknown$2.80$14.001,048,576100.0%