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

Modal

Official site · origin not confirmed

Models it serves

5 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-Flashnvfp4$0.15$0.501,048,57699.9%
DeepSeek V4.1 Flashunknown$0.30$1.201,048,576100.0%
GLM-5.3unknown$1.40$4.401,048,57699.9%
Qwen3.8 2.4T A95Bunknown$2.00$6.001,000,000—
Kimi K3mxfp4$3.00$15.001,048,576100.0%