Groq

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.

Models (17)

	Organization	Model Name	Provider Model	Input ($/1M)	Output ($/1M)	Free	Weekly
	OpenAI	GPT OSS 120B	openai/gpt-oss-120b	$0.15	$0.60
	Moonshot AI	Kimi K2-Instruct-0905	moonshotai/kimi-k2-instruct-0905	$1.00	$3.00
	Moonshot AI	Kimi K2 Instruct	moonshotai/kimi-k2-instruct	$1.00	$3.00
	OpenAI	GPT OSS 20B	openai/gpt-oss-20b	$0.08	$0.30
	DeepSeek	DeepSeek R1 Distill Llama 70B	deepseek-r1-distill-llama-70b	$0.75	$0.99
	Groq	Llama 3.1 8B Instant	llama-3.1-8b-instant	$0.05	$0.08
	Groq	Mistral Saba 24B	mistral-saba-24b	$0.79	$0.79
	Groq	Llama 3 8B	llama3-8b-8192	$0.05	$0.08
	Groq	Qwen QwQ 32B	qwen-qwq-32b	$0.29	$0.39
	Groq	Llama 3 70B	llama3-70b-8192	$0.59	$0.79
	Groq	Llama Guard 3 8B	llama-guard-3-8b	$0.20	$0.20
	Google	Gemma 2 9B	gemma2-9b-it	$0.20	$0.20
	Groq	Llama 3.3 70B Versatile	llama-3.3-70b-versatile	$0.59	$0.79
	Alibaba Cloud / Qwen Team	Qwen3 32B	qwen/qwen3-32b	$0.29	$0.59
	Meta	llama-4-scout-17b-16e-instruct	meta-llama/llama-4-scout-17b-16e-instruct	$0.11	$0.34
	Meta	llama-4-maverick-17b-128e-instruct	meta-llama/llama-4-maverick-17b-128e-instruct	$0.20	$0.60
	Groq	Llama Guard 4 12B	meta-llama/llama-guard-4-12b	$0.20	$0.20