Inference provider

Groq

Headquarters: US

8

models

8

endpoints

Groq website preview
Groq website

Catalogue

Available models

ModelEndpointContextInput /MOutput /MCached input /MCache write /MUptime 1d
Llama 3.1 8B Instructgroq131K$0.05$0.08$0.02—100.00%
Llama 3.3 70B Instructgroq131K$0.59$0.79$0.30—100.00%
MiniMax M2.7groq197K$0.60$1.80——91.16%
Whisper Large V3groq—$30.83$0.00——100.00%
Whisper Large V3 Turbogroq—$11.11$0.00——100.00%
gpt-oss-120bgroq131K$0.15$0.60$0.08—100.00%
gpt-oss-20bgroq131K$0.08$0.30$0.04—99.93%
gpt-oss-safeguard-20bgroq131K$0.08$0.30$0.04—100.00%