Inference provider

BaseTen

Headquarters: US

9

models

22

endpoints

BaseTen website preview
BaseTen website

Catalogue

Available models

ModelEndpointContextInput /MOutput /MCached input /MCache write /MUptime 1d
DeepSeek V4 Flash 0731baseten/fp81.0M$0.13$0.26$0.03—99.30%
DeepSeek V4 Flash 0731baseten/fp8/us1.0M$0.13$0.26$0.03—98.89%
DeepSeek V4.1 Flashbaseten/fast1.0M$0.60$2.40$0.01—99.79%
DeepSeek V4.1 Flashbaseten/fp321.0M$0.30$1.20$0.007—99.80%
DeepSeek V4.1 Flashbaseten/fp81.0M$0.30$1.20$0.007—100.00%
GLM 5.2baseten/fast1.0M$2.10$6.60$0.21—100.00%
GLM 5.2baseten/fp81.0M$1.40$4.40$0.14—100.00%
GLM 5.2baseten/fp8/us1.0M$1.40$4.40$0.14—100.00%
GLM 5.2baseten/us/fast1.0M$2.10$6.60$0.21—100.00%
GLM 5.3baseten/fast1.0M$2.10$6.60$0.21—100.00%
GLM 5.3baseten/fp41.0M$1.40$4.40$0.14—100.00%
GLM 5.3baseten/fp4/us1.0M$1.40$4.40$0.14—100.00%
GLM 5.3baseten/us/fast1.0M$2.10$6.60$0.21—99.89%
GLM 5.3 Flashbaseten/fp81.0M$0.15$0.50$0.03—95.49%
GLM 5.3 Flashbaseten/fp8/us1.0M$0.15$0.50$0.03—96.32%
Kimi K3baseten/fp81.0M$3.00$15.00$0.30—100.00%
Nemotron 3 Ultrabaseten/fp4203K$0.60$2.40$0.12—100.00%
Nemotron 3 Ultrabaseten/fp4/us203K$0.60$2.40$0.12—99.92%
gpt-oss-120bbaseten/fp4128K$0.10$0.50$0.10—100.00%
gpt-oss-120bbaseten/fp4/us128K$0.10$0.50$0.10—100.00%