Rocket - Think it. Type it. Launch it.
Mini toolsGroq
Established in 2016 for inference, Groq is literally built different. It’s the only custom-built inference chip that fuels developers with the performance they need at a cost that doesn’t hold them back.
AI Native
Yes
Number of tools
0
Valuation
$6.90BAI
Models
-
Groq Llama is Meta’s Llama family served on Groq hardware, giving Llama-quality outputs with very low latency.TextReleased 1y ago
-
Groq Gemma is Google’s Gemma model family served on Groq hardware for ultra-low-latency inference. You get Gemma’s capabilities with extremely fast response times.TextReleased 2y ago
