Groq

Cloud PlatformOpenAI compatible

Ultra-fast inference platform powered by custom LPU hardware for low-latency AI.

Active models

16

Families

8

Headquarters🇺🇸 Mountain View, CA

Founded2016

API Base URL

Modelsconsole.groq.com/docs/models

Type

OSS

Model	Caps	Context	Pricing
Llama 4 Scout 17B 16EOSSmeta-llama/llama-4-scout-17b-16e-instruct	RVTSJF	131K	$0.11$0.34
Llama 3.3 70Bllama-3.3-70b-versatile	RVTSJF	131K	$0.59$0.79
Llama 3.1 8Bllama-3.1-8b-instant	RVTSJF	131K	$0.05$0.08
Qwen3-32Bqwen/qwen3-32b	RVTSJF	131K	$0.29$0.59
Kimi K2 0905moonshotai/kimi-k2-instruct-0905	RVTSJF	262K	$1$3
GPT OSS 120BOSSopenai/gpt-oss-120b	RTSJ	131K	$0.15$0.6
GPT OSS 20BOSSopenai/gpt-oss-20b	RTSJ	131K	$0.08$0.3
Compoundgroq/compound	RVTSJF	131K
Compound Minigroq/compound-mini	RVTSJF	131K
Whisper Large V3 Turbowhisper-large-v3-turbo

1–10 of 16

1 / 2