Skip to main content
Version: v0.3.2

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_models<class 'bool'>NoFalseWhether to refresh models periodically from the provider
api_keypydantic.types.SecretStr | NoneNoAuthentication credential for the provider
url<class 'str'>Nohttps://api.groq.comThe URL for the Groq AI server

Sample Configuration​

url: https://api.groq.com
api_key: ${env.GROQ_API_KEY:=}