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

Novita

Official site · origin not confirmed

Models it serves

33 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
Ling-3.0-flashunknown$0.02$0.06262,144100.0%
gpt-oss-20bfp4$0.04$0.15131,072100.0%
Nemotron 3 Nano 30Bfp4$0.05$0.20262,1440.0%
gpt-oss-120bfp4$0.05$0.25131,07283.1%
Gemma 3 27Bbf16$0.12$0.2098,30499.3%
DeepSeek V4 Flashfp8$0.14$0.281,048,57699.7%
Gemma 4 26B A4B bf16$0.13$0.40262,14498.5%
Gemma 4 31Bbf16$0.14$0.40262,14493.1%
Xiaomi MiMo-V2.5fp8$0.17$0.341,048,57699.1%
Ring-2.6-1Tunknown$0.07$0.62262,144100.0%
Tencent Hy3unknown$0.14$0.58262,144100.0%
Llama 4 Scoutbf16$0.18$0.59131,07299.9%
DeepSeek V3.2fp8$0.27$0.40163,84099.9%
Llama 4 Maverickfp8$0.27$0.851,048,57699.0%
Step 3.7 Flashfp8$0.20$1.15262,14499.1%
DeepSeek V3.1 Terminusfp8$0.27$1.00131,072100.0%
MiniMax M2.7fp8$0.27$1.08204,80098.2%
DeepSeek V3 0324fp8$0.27$1.12163,84099.9%
MiniMax-M3fp8$0.30$1.201,000,00099.7%
Qwen3 Coder Nextfp8$0.20$1.50262,144100.0%
Xiaomi MiMo-V2.5-Prounknown$0.48$0.961,048,576100.0%
DeepSeek V3fp8$0.40$1.3064,000100.0%
GLM 4.7fp8$0.54$1.98204,80095.4%
GLM 4.6bf16$0.55$2.20204,80098.5%
Qwen3.5-122B-A10Bbf16$0.40$3.20262,14499.8%
GLM-5.2fp8$0.74$2.331,048,57699.3%
Kimi K2.5unknown$0.57$2.85262,14497.5%
DeepSeek R1fp8$0.70$2.5064,000100.0%
Qwen3.5 397B A17Bunknown$0.60$3.60262,14499.3%
Kimi K2.6unknown$0.80$3.40262,14499.9%
Kimi K2.7 Codeint4$0.91$3.84262,144100.0%
DeepSeek V4 Profp8$1.32$3.961,048,57699.7%
GLM-5.1fp8$1.38$4.40204,800100.0%
◆ 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.