All Groq Models
GroqAPI REFERENCE
Llama 3.3 70B (Groq)
Ultra-fast inference on LPU™ technology for Meta's Llama 3.3 architecture.
READ GUIDE
GroqAPI REFERENCE
Llama 3.1 8B (Groq)
Compact Llama instruction model running on Groq's high-speed LPU™.
READ GUIDE
GroqAPI REFERENCE
DeepSeek R1 70B (Groq)
DeepSeek's reasoning model distilled into the Llama 70B architecture on LPU.
READ GUIDE
GroqAPI REFERENCE
Mixtral 8x7B (Groq)
Fast open MoE (Mixture of Experts) model by Mistral AI running on Groq LPUs.
READ GUIDE
GroqAPI REFERENCE
Gemma 2 9B (Groq)
Google's open-weight Gemma 2 model running efficiently on Groq LPUs.
READ GUIDE
GroqAPI REFERENCE
Llama Guard 3 8B (Groq)
Safety model for policy screening, moderation, and risk-aware workflows.
READ GUIDE
GroqAPI REFERENCE
Whisper Large V3 (Groq)
Speech transcription model optimized for fast audio-to-text workflows.
READ GUIDE
