Inference provider

Wafer

Headquarters: US

11

models

14

endpoints

Wafer website preview
Wafer website

Catalogue

Available models

ModelEndpointContextInput /MOutput /MCached input /MCache write /MUptime 1d
DeepSeek V4 Flash 0423wafer1.0M$0.48$0.17$0.01—99.79%
DeepSeek V4 Flash 0731wafer/fast1.0M$0.13$0.23$0.13—100.00%
DeepSeek V4 Pro 0813wafer1.0M$0.25$5.00$0.25—100.00%
DeepSeek V4.1 Flashwafer1.0M$0.10$0.65$0.02—98.75%
GLM 5.2wafer1.0M$0.19$8.00$0.18—99.93%
GLM 5.2wafer/us1.0M$0.02$7.00$0.02—100.00%
GLM 5.3wafer1.0M$0.03$4.80$0.03—100.00%
GLM 5.3wafer/us1.0M$0.08$4.80$0.08—100.00%
GLM 5.3 Flashwafer1.0M$0.12$0.50$0.06—100.00%
Kimi K3wafer1.0M$0.29$24.00$0.28—100.00%
Kimi K3wafer/us1.0M$0.33$14.90$0.32—100.00%
Nemotron 3.5 Lightningwafer262K$0.04$0.13$0.02—100.00%
Qwen3.8 27Bwafer262K$0.04$2.30$0.04—100.00%