Skip to main content
Version: v0.4.0

remote::groq

Description​

Groq inference provider for ultra-fast inference using Groq's LPU technology.

Configuration​

FieldTypeRequiredDefaultDescription
allowed_modelslist[str] | NoneNoList of models that should be registered with the model registry. If None, all models are allowed.
refresh_modelsboolNoFalseWhether to refresh models periodically from the provider
api_keySecretStr | NoneNoAuthentication credential for the provider
base_urlHttpUrl | NoneNohttps://api.groq.com/openai/v1The URL for the Groq AI server

Sample Configuration​

base_url: https://api.groq.com/openai/v1
api_key: ${env.GROQ_API_KEY:=}