Inference provider

OpenInference

Headquarters: US

4

models

4

endpoints

Catalogue

Available models

ModelEndpointContextInput /MOutput /MCached input /MCache write /MUptime 1d
DeepSeek V4 Flash 0423open-inference/fp41.0M$0.05$1.15$0.01—95.60%
DeepSeek V4 Flash 0731open-inference/fp41.0M$0.01$0.58$0.01—96.25%
DeepSeek V4.1 Flashopen-inference/fp41.0M$0.02$0.72$0.0054—97.85%
GLM 5.3 Flashopen-inference/fp41.0M$0.04$0.90$0.01—95.83%