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

DigitalOcean

Official site · 🇺🇸 United States

Models it serves

12 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 Flashunknown$0.08$0.251,048,57699.1%
gpt-oss-120bunknown$0.06$0.39128,000100.0%
Nemotron 3 Super 120Bunknown$0.17$0.361,000,00092.9%
Llama 4 Maverickunknown$0.20$0.70128,000100.0%
DeepSeek V3.2unknown$0.25$0.80163,84098.4%
Xiaomi MiMo-V2.5-Prounknown$0.40$1.50262,144100.0%
Qwen3.5 397B A17Bunknown$0.30$1.93131,072100.0%
Kimi K2.5unknown$0.38$2.02262,14498.4%
GLM-5.2unknown$0.63$1.98262,144100.0%
Kimi K2.6unknown$0.76$3.20262,14499.6%
GLM-5.1unknown$0.97$4.30163,84092.6%
Kimi K3unknown$2.85$14.251,048,57699.8%
◆ 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.