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

Together

Official site · 🇺🇸 United States

Models it serves

15 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
Gemma 3n E4Bunknown$0.06$0.1232,768100.0%
gpt-oss-20bunknown$0.05$0.20131,072
DeepSeek V4 Flashunknown$0.14$0.281,048,57697.1%
Qwen3.5-9Bunknown$0.17$0.25262,14499.6%
gpt-oss-120bunknown$0.15$0.60131,07294.9%
Gemma 4 31Bunknown$0.28$0.86262,144
MiniMax-M3unknown$0.30$1.20524,28899.5%
Gemma 4 31Bunknown$0.39$0.97262,144
Muse Glimmerunknown$0.35$1.50131,07299.7%
Nemotron 3 Ultra 550Bunknown$0.60$3.60512,28898.2%
Kimi K2.7 Codeunknown$0.95$4.00262,14498.7%
Inklingunknown$1.00$4.05524,288100.0%
Kimi K2.6unknown$1.20$4.50262,14495.0%
GLM-5.2unknown$1.40$4.40512,00099.1%
Kimi K3unknown$3.00$15.001,000,00099.1%
◆ 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.