Inference provider

Novita

Headquarters: US

59

models

59

endpoints

Novita website preview
Novita website

Catalogue

Available models

ModelEndpointContextInput /MOutput /MCached input /MCache write /MUptime 1d
DeepSeek V4 Flash 0731novita/fp81.0M$0.41$1.23$0.03—100.00%
DeepSeek V4 Pro 0423novita/fp81.0M$1.60$3.20$0.14—94.27%
DeepSeek V4 Pro 0813novita/fp81.0M$0.99$2.97$0.03—88.18%
DeepSeek V4.1 Flashnovita/fp81.0M$0.20$0.78$0.0039—100.00%
GLM 4.5 Airnovita/bf16131K$0.13$0.85$0.02—100.00%
GLM 4.5Vnovita/fp866K$0.60$1.80$0.11—95.65%
GLM 4.6novita/bf16205K$0.55$2.20$0.11—100.00%
GLM 4.6Vnovita/bf16131K$0.30$0.90$0.06—100.00%
GLM 4.7novita/fp8205K$0.54$1.98$0.10—100.00%
GLM 4.7 Flashnovita/bf16200K$0.07$0.40$0.01—7.06%
GLM 5novita/fp8203K$1.00$3.20$0.20—100.00%
GLM 5.1novita/fp8205K$1.38$4.40$0.26—100.00%
GLM 5.2novita/fp81.0M$0.65$2.04$0.12—100.00%
GLM 5.3novita/fp81.0M$0.70$2.20$0.13—99.21%
GLM 5.3 Flashnovita/fp81.0M$0.08$0.28$0.02—98.68%
Gemma 3 27Bnovita/bf1698K$0.12$0.20——95.75%
Gemma 4 26B A4Bnovita/bf16262K$0.13$0.40——100.00%
Gemma 4 31Bnovita/bf16262K$0.14$0.40——62.71%
Hy3novita262K$0.14$0.58$0.04—100.00%
Hy4 previewnovita/fp81M$0.83$2.50$0.04—99.82%
Kimi K2 0711novita/fp8131K$0.57$2.30——100.00%
Kimi K2 0905novita/fp8262K$0.60$2.50——100.00%
Kimi K2 Thinkingnovita/bf16262K$0.60$2.50$0.15—100.00%
Kimi K2.5novita262K$0.57$2.85$0.10—97.85%
Kimi K2.6novita262K$0.80$3.40$0.16—98.38%
Kimi K2.7 Codenovita/int4262K$0.91$3.84$0.18—100.00%
Ling 3.0 Flashnovita262K$0.02$0.06$0.0042—100.00%
Ling 3.1 Flashnovita262K$0.08$0.22$0.02—100.00%
Llama 3.1 8B Instructnovita/fp816K$0.02$0.05——97.99%
Llama 3.3 70B Instructnovita/bf1612K$0.14$0.40——96.81%
Llama 4 Mavericknovita/fp81.0M$0.27$0.85——100.00%
Llama 4 Scoutnovita/bf16131K$0.18$0.59——85.63%
MiMo-V2.5novita/fp81.0M$0.17$0.34$0.0034—72.20%
MiMo-V2.5-Pronovita1.0M$0.48$0.96$0.003956—98.03%
MiMo-V2.6-Flashnovita/fp81.0M$0.14$0.28$0.0028—98.89%
MiMo-V2.6-Pronovita/fp81.0M$0.44$0.87$0.0036—93.13%
MiniMax M1novita/bf161M$0.55$2.20——100.00%
MiniMax M2.5novita/fp8205K$0.30$1.20$0.03—100.00%
MiniMax M2.7novita/fp8205K$0.27$1.08$0.05—99.81%
MiniMax M3novita/fp81M$0.30$1.20$0.06—99.55%
Nemotron 3 Nano 30B A3Bnovita/fp4262K$0.05$0.20——100.00%
Qwen3 VL 30B A3B Instructnovita/bf16131K$0.20$0.70——93.63%
Qwen3.5 397B A17Bnovita262K$0.60$3.60——99.25%
Qwen3.5-122B-A10Bnovita/bf16262K$0.40$3.20——99.79%
Qwen3.5-27Bnovita/bf16262K$0.30$2.40——100.00%
Qwen3.8 2.4T A95Bnovita1M$2.00$6.00$0.25—99.91%
Qwen3.8 27Bnovita1M$0.42$3.00$0.08—99.82%
R1novita/fp864K$0.70$2.50——100.00%
R1 0528novita/fp8164K$0.70$2.50$0.35—99.84%
Step 3.7 Flashnovita/fp8262K$0.20$1.15$0.04—100.00%
WizardLM-2 8x22Bnovita/bf1666K$0.62$0.62——99.52%
gpt-oss-120bnovita/fp4131K$0.05$0.25——99.93%