switchboard
groq
Low-latency inference API running open models on custom LPU hardware, with an OpenAI-compatible interface and tool-calling support.
fields
nameGroq
providerGroq
urlhttps://console.groq.com/docs
categorieslanguage · infrastructure
accessapi
authapiKey
streamingtrue
pushfalse
verifiedfalse
tagsfast-inference, lpu, low-latency, openai-compatible