Groq

groq

Chat Code

Updated 1 hour ago

Groq is an AI inference company that pioneered the LPU (Language Processing Unit) in 2016, the first chip purpose-built for AI inference. Their proprietary LPU inference engine delivers ultra-low latency AI inference, with benchmarks showing Llama 2 70B running at 300 tokens per second—reportedly 10x faster than NVIDIA H100 clusters and 18x faster on Anyscale's LLMPerf Leaderboard. Groq focuses on making AI inference fast and affordable at scale, offering both cloud services and on-premises deployment options, with a mission to enable real-time AI applications that were previously impossible due to latency constraints.

Visit Website LLMs.txt

Browse 15 LLM models available from Groq. Compare prices and features.

Models (15)

Organization	Model Name	Original Model	Input	Output
OpenAI	GPT OSS 120B	`openai/gpt-oss-120b`	$0.15	$0.60	View
OpenAI	GPT OSS 20B	`openai/gpt-oss-20b`	$0.08	$0.30	View
qwen	Qwen3 32B	`qwen/qwen3-32b`	$0.29	$0.59	View
Nvidia	Whisper Large v3	`whisper-large-v3`	-	-	View
Groq	Whisper Large v3 Turbo	`whisper-large-v3-turbo`	-	-	View
OpenAI	gpt-oss-safeguard-20b	`openai/gpt-oss-safeguard-20b`	$0.08	$0.30	View
Groq	Compound	`groq/compound`	-	-	View
Groq	Compound Mini	`groq/compound-mini`	-	-	View
Groq	Llama 3.1 8B Instant	`llama-3.1-8b-instant`	$0.05	$0.08	View
Groq	Llama 3.3 70B Versatile	`llama-3.3-70b-versatile`	$0.59	$0.79	View
Groq	Llama Prompt Guard 2 22M	`meta-llama/llama-prompt-guard-2-22m`	$0.03	$0.03	View
Groq	Llama Prompt Guard 2 86M	`meta-llama/llama-prompt-guard-2-86m`	$0.04	$0.04	View
Meta	llama-4-scout-17b-16e-instruct	`meta-llama/llama-4-scout-17b-16e-instruct`	$0.11	$0.34	View
Groq	Orpheus Arabic Saudi	`canopylabs/orpheus-arabic-saudi`	-	-	View
Groq	Orpheus V1 English	`canopylabs/orpheus-v1-english`	-	-	View

Back to Providers Visit Website